wshobson--agents
Seth Hobson
be57c0b2e3
* feat(adapters): multi-harness framework + harness_portability eval dimension
Turn this Claude Code plugin marketplace into a generic agentic-harness
marketplace. Adapters under tools/adapters/ emit harness-native artifacts
for OpenAI Codex CLI, Cursor, OpenCode, and Gemini CLI from a single
Markdown source. Source-of-truth stays under plugins/ — Claude Code is
unchanged.
Framework (tools/adapters/):
- base.py — PluginSource parser, HarnessAdapter ABC, write/mirror helpers
(path-traversal guard, UTF-8-safe), inline-list + block-list + block-scalar
YAML-ish parser, _utf8_safe_cut, _split_inline_list, _normalize_author
- capabilities.py — per-harness capability matrix, TOOL_NAME_MAPS,
MODEL_ALIASES, resolve_model() with explicit warnings
- codex.py — emits .codex/{skills,agents}/ + AGENTS.md (≤150-line
table-of-contents). Fence-aware body splitter, _utf8_safe_cut for
multibyte safety, _yaml_scalar with reserved-word + special-char quoting.
Skill/command name collision detection (and second-order __cmd fallback).
- cursor.py — emits .cursor-plugin/{plugin,marketplace}.json + curated
.cursor/rules/*.mdc. _validate_mdc_frontmatter handles YAML block scalars
(no false positives on colons in description body). _normalize_author
handles dict, npm-style strings, and author lists.
- opencode.py — transpiles agents to .opencode/agents/<id>.md with
mode:subagent + permission: deny-everything-else block (skill/task always
allowed as base capabilities — Claude's implicit defaults).
- gemini.py — emits native skills/, agents/, and commands/ at extension
root (April 2026 spec). Tool-allowlist remapped via TOOL_NAME_MAPS.
CLI + tooling:
- tools/generate.py — unified `make generate HARNESS=<x> [PLUGIN=<y>]`,
with --clean (containment-guarded; case-insensitive on Darwin/Win32),
--prune (orphan removal across all per-harness output trees), --strict
(warnings fail), per-plugin error aggregation, refuses --clean --plugin
(would silently wipe other plugins' artifacts).
- tools/validate_generated.py — structural validation across all four
harness outputs. Codex 8KB cap → error. _extract_permission_block
correctly handles nested permission keys (column-0 only).
- tools/doc_gardener.py — recurring drift detection per OpenAI harness-
engineering principle. STALE_ARTIFACT (info), DEAD_LINK (error),
MARKETPLACE_ORPHAN (error), SKILL_OVER_CODEX_CAP (warning), grouped
output sorted by severity.
plugin-eval (extends existing framework):
- New harness_portability dimension (6% weight, rebalanced from existing
static sub-scores). Surfaces non-portable patterns with concrete
remediation hints: SKILL_OVER_CODEX_CAP, CLAUDE_TOOL_REFS,
CLAUDE_TOOL_PROSE, AGENT_NAME_COLLISION, BARE_MODEL_ALIAS.
- _CAMEL_TOOL_PATTERN requires Claude-tool context (no false positives
on Rust's `Task` etc.). _TOOL_PROSE_PATTERN case-sensitive on tool
names, case-insensitive on the leading article.
- Findings do NOT also feed anti_pattern_penalty (no double-counting).
Documentation:
- Top-level guides: CODEX.md, CURSOR.md, OPENCODE.md (≤150 lines each,
table-of-contents pattern per OpenAI harness-engineering post)
- docs/harnesses.md — capability matrix, graceful-degradation table,
generated output paths
- docs/authoring.md — portable-content style guide (tools, models,
collision rules, fence-respect)
- docs/round-trip-results.md — real-CLI verification recipes (OpenCode
discovers 193 subagents, Gemini extensions validate passes, Codex
TOMLs all parse)
- CONTRIBUTING.md — new file pointing at docs/authoring.md
- README.md — rewritten for multi-harness (145 lines, was 460)
- CLAUDE.md — trimmed to 60-line table-of-contents
- GEMINI.md — trimmed from 1500 to 500 tokens (3× over budget previously)
Tests: 181 passing (103 plugin-eval + 78 tools/tests). Real-CLI round-trip
verified for OpenCode, Gemini, and Codex (TOML parses).
Replaces tools/generate_gemini_commands.py with the unified CLI.
* refactor(skills): extract detail to references/details.md (~75 skills)
Apply Anthropic's canonical SKILL.md progressive-disclosure pattern across
the marketplace: SKILL.md body becomes a navigation tier (trigger phrasing
+ quick start), detailed templates and worked examples move to
references/details.md (loaded on demand by the agent).
Motivation: OpenAI Codex CLI hard-truncates skills at 8 KB. Before this
change, ~90 skills exceeded that cap and would silently break on Codex.
The progressive-disclosure pattern is also Anthropic's documented
recommendation for token efficiency — Claude Code reads references/ files
on demand when the body navigation says to.
What's extracted, by pattern:
- Pass 1 (## Templates section): 19 skills — full template libraries
moved to references/details.md
- Pass 2 (## Implementation Patterns / ## Advanced Patterns): 13 skills
- Pass 3 (everything between nav-tier and wrap-tier headings): 53 skills
- Conservative re-extraction for 8 skills that got over-reduced — kept
~6-7 KB inline (most of the quick-start tier) plus references/ overflow
What stays inline (SKILL.md navigation tier):
- description: frontmatter (triggering — unchanged for all skills)
- ## When to Use This Skill / ## Core Concepts / ## Quick Start
- ## Best Practices / ## Troubleshooting / ## See Also wrap-ups
- A pointer note ("see references/details.md") so the agent knows where
to look for detail
What goes to references/details.md (detail tier, on-demand load):
- ## Templates (full code template libraries)
- ## Implementation Patterns / ## Advanced Patterns (deep examples)
- Mid-skill walkthroughs that exceed the inline budget
Also in this commit:
- plugins/brand-landingpage description trimmed from 958→543 chars
(preserves trigger phrasing, drops verbose example-quote list)
Net effect:
- SKILL_OVER_CODEX_CAP findings: 90 → 10 (88% reduction)
- All triggers unchanged — discovery behavior identical across harnesses
- 75 new references/details.md files with the extracted content
- Same depth of guidance, loaded progressively
Remaining 10 oversized skills are complex multi-section docs (e.g.
postgresql, code-review-excellence, evaluation-methodology) that need
per-skill manual judgment — flagged by `make garden` for future work.
* chore: bump all plugin versions (multi-harness release)
Patch-bump every local plugin (81) in both .claude-plugin/marketplace.json
entries and each plugins/<name>/.claude-plugin/plugin.json. Minor-bump the
top-level marketplace metadata.version (1.6.0 → 1.7.0) to signal the
multi-harness adapter framework addition.
The external git-subdir entry (qa-orchestra) is unaffected — its version
is governed by its upstream repo.
* fix(opencode): preserve explicit tools:[] + word-boundary subtask match
Addresses two Codex review findings on PR #541.
## P1 — `tools: []` silently upgraded to permissive (privilege escalation)
Before: `_build_permission_block` returned `{}` for any empty list, which
omits the `permission:` block entirely from the emitted agent. An author
who explicitly wrote `tools: []` to lock down an advisory-only agent got
an UNRESTRICTED agent in OpenCode. Affected agent in this tree:
`plugins/arm-cortex-microcontrollers/agents/arm-cortex-expert.md`.
Fix: `_build_permission_block` now takes a `has_tools_field` flag so the
caller can distinguish "tools: key missing" (Claude default permissive)
from "tools: []" (explicit lock-down). The lock-down case emits a
deny-everything block that allows ONLY the base capabilities (skill, task)
that Claude Code always grants implicitly. Verified against the real
arm-cortex-expert agent — now emits read/edit/write/bash/grep/glob/list:
deny, task/skill: allow.
## P2 — `"agent" in cmd.body.lower()` false-positives on substrings
Before: a command body containing `PerformanceReviewAgent` (class name
in a code snippet) or `useragent` triggered `subtask: true`, changing
runtime behavior based on incidental text.
Fix: switch to a compiled word-boundary regex `\b(agent|subagent)s?\b`
(case-insensitive). Tests confirm the substring `PerformanceReviewAgent`
no longer fires, while a real "spawn a subagent" sentence still does.
## Tests
3 new regression tests in tools/tests/test_adapters.py:
- `test_explicit_empty_tools_yields_locked_permission_block` (P1)
- `test_missing_tools_field_yields_no_permission_block` (P1 boundary)
- `test_subtask_inference_word_boundary` (P2)
184 total tests pass (was 181). OpenCode round-trip still discovers all
193 subagents; arm-cortex-expert agent is now properly locked down.
* test: behavioral verification + CI gates for multi-harness pipeline
Adds three layers of automated verification that pure-Python parser tests
miss, plus the CI jobs that turn them into hard gates. Catches the kinds
of issues that previously only surfaced when a real user installed the
marketplace and tried to use it.
## test_real_world.py — real-source structural tests
Runs against the actual `plugins/` tree (not synthetic fixtures). Catches
issues that only appear on real content:
- every marketplace entry resolves to a plugins/<name>/ dir
- every local plugin dir appears in marketplace.json
- marketplace.json version == per-plugin plugin.json version (catches drift)
- every plugin loads via load_plugin() without error
- no plugin name contains `__` (adapter namespace separator)
- every agent has name + description; every skill has a trigger phrase
(same regex plugin_eval's MISSING_TRIGGER check uses)
- no agent name collides with Codex built-ins
- every refactored skill (with `references/details.md`) has:
- meaningful detail content (>=500 B in details.md)
- a pointer to references/ in the SKILL.md body
- a navigation-tier heading preserved (When to Use, Overview, etc.)
- body >= 600 B (not a stub)
- every plugin.json has name + version matching the dir
This test pass found and fixed three real defects before commit:
- ship-mate/skills/scan: description had no trigger phrase ("Use when…")
- reverse-engineering/skills/memory-forensics: nav-tier section lost
during extraction
- reverse-engineering/skills/binary-analysis-patterns: same
All three are now fixed (preserved trigger phrasing, added When-to-Use
sections back to the skills my extraction over-trimmed).
## test_round_trip.py — generate→parse→verify
CI runs this AFTER `make generate-all`. Catches generation-time regressions:
- OpenCode/Codex/Gemini agent counts match source agent count (no skips)
- every Codex SKILL.md under 8 KB (the cap that would silently truncate)
- every Codex agent TOML has required fields + valid sandbox_mode
- every OpenCode agent has mode in {primary,subagent,all} and
provider-prefixed model
- locked agents (source `tools: []`) emit proper deny-everything permission
block with skill/task allow (regression guard for PR-541 P1)
- every Gemini @{path} injection resolves to a real source file
- every Gemini command TOML has prompt + {{args}} placeholder
- every context file (CLAUDE.md, AGENTS.md, GEMINI.md, etc.) within
150-line cap
- Cursor marketplace + per-plugin manifests cover all local plugins
- .cursor/rules/*.mdc only use the 3 documented frontmatter keys
## test_cli_smoke.py — real-CLI subprocess tests
Invokes the actual harness binaries (OpenCode, Gemini, Codex, Claude Code)
against the generated artifacts. Catches CLI-level issues pure-Python
parsing can't see: schema-loader drift, plugin-discovery bugs, version
incompatibilities.
- `opencode agent list` — must succeed AND discover every source agent
(currently 191 + 2 OpenCode built-ins)
- `gemini extensions validate <repo>` — must return success
- `codex doctor` — must report healthy install
- every Codex agent TOML must parse with stdlib `tomllib`
- `claude --version` — sanity check the Claude Code CLI loads
- marketplace.json must have owner + metadata.version for Claude Code's loader
Per-CLI tests skip gracefully when the binary isn't on PATH, so local
devs only exercise what they have installed. CI installs OpenCode +
Gemini and turns those skips into hard gates.
## Makefile + CI
- `make test` — full pytest suite (plugin-eval + tools/tests/)
- `make smoke-test` — generates if needed, then runs real-CLI smoke tests
- `.github/workflows/validate.yml` extended with:
- `tools-tests` job — runs pytest tools/tests/
- `multi-harness-generate` job — `make generate-all && make validate
STRICT=1 && make garden`, uploads generated artifacts on every run
- `cli-smoke-test` job — installs OpenCode + Gemini, runs test_cli_smoke.py
## Test counts
- Before: 184 tests
- After: 386 tests (parameterized real-source tests over all 82 plugins)
- All passing locally on OpenCode 1.15.7 + Gemini 0.42.0 + Codex 0.133.0
+ Claude Code 2.1.148
12 KiB
12 KiB
openapi-spec-generation — templates and worked examples
Templates
Template 1: Complete API Specification
openapi: 3.1.0
info:
title: User Management API
description: |
API for managing users and their profiles.
## Authentication
All endpoints require Bearer token authentication.
## Rate Limiting
- 1000 requests per minute for standard tier
- 10000 requests per minute for enterprise tier
version: 2.0.0
contact:
name: API Support
email: api-support@example.com
url: https://docs.example.com
license:
name: MIT
url: https://opensource.org/licenses/MIT
servers:
- url: https://api.example.com/v2
description: Production
- url: https://staging-api.example.com/v2
description: Staging
- url: http://localhost:3000/v2
description: Local development
tags:
- name: Users
description: User management operations
- name: Profiles
description: User profile operations
- name: Admin
description: Administrative operations
paths:
/users:
get:
operationId: listUsers
summary: List all users
description: Returns a paginated list of users with optional filtering.
tags:
- Users
parameters:
- $ref: "#/components/parameters/PageParam"
- $ref: "#/components/parameters/LimitParam"
- name: status
in: query
description: Filter by user status
schema:
$ref: "#/components/schemas/UserStatus"
- name: search
in: query
description: Search by name or email
schema:
type: string
minLength: 2
maxLength: 100
responses:
"200":
description: Successful response
content:
application/json:
schema:
$ref: "#/components/schemas/UserListResponse"
examples:
default:
$ref: "#/components/examples/UserListExample"
"400":
$ref: "#/components/responses/BadRequest"
"401":
$ref: "#/components/responses/Unauthorized"
"429":
$ref: "#/components/responses/RateLimited"
security:
- bearerAuth: []
post:
operationId: createUser
summary: Create a new user
description: Creates a new user account and sends welcome email.
tags:
- Users
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/CreateUserRequest"
examples:
standard:
summary: Standard user
value:
email: user@example.com
name: John Doe
role: user
admin:
summary: Admin user
value:
email: admin@example.com
name: Admin User
role: admin
responses:
"201":
description: User created successfully
content:
application/json:
schema:
$ref: "#/components/schemas/User"
headers:
Location:
description: URL of created user
schema:
type: string
format: uri
"400":
$ref: "#/components/responses/BadRequest"
"409":
description: Email already exists
content:
application/json:
schema:
$ref: "#/components/schemas/Error"
security:
- bearerAuth: []
/users/{userId}:
parameters:
- $ref: "#/components/parameters/UserIdParam"
get:
operationId: getUser
summary: Get user by ID
tags:
- Users
responses:
"200":
description: Successful response
content:
application/json:
schema:
$ref: "#/components/schemas/User"
"404":
$ref: "#/components/responses/NotFound"
security:
- bearerAuth: []
patch:
operationId: updateUser
summary: Update user
tags:
- Users
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/UpdateUserRequest"
responses:
"200":
description: User updated
content:
application/json:
schema:
$ref: "#/components/schemas/User"
"400":
$ref: "#/components/responses/BadRequest"
"404":
$ref: "#/components/responses/NotFound"
security:
- bearerAuth: []
delete:
operationId: deleteUser
summary: Delete user
tags:
- Users
- Admin
responses:
"204":
description: User deleted
"404":
$ref: "#/components/responses/NotFound"
security:
- bearerAuth: []
- apiKey: []
components:
schemas:
User:
type: object
required:
- id
- email
- name
- status
- createdAt
properties:
id:
type: string
format: uuid
readOnly: true
description: Unique user identifier
email:
type: string
format: email
description: User email address
name:
type: string
minLength: 1
maxLength: 100
description: User display name
status:
$ref: "#/components/schemas/UserStatus"
role:
type: string
enum: [user, moderator, admin]
default: user
avatar:
type: string
format: uri
nullable: true
metadata:
type: object
additionalProperties: true
description: Custom metadata
createdAt:
type: string
format: date-time
readOnly: true
updatedAt:
type: string
format: date-time
readOnly: true
UserStatus:
type: string
enum: [active, inactive, suspended, pending]
description: User account status
CreateUserRequest:
type: object
required:
- email
- name
properties:
email:
type: string
format: email
name:
type: string
minLength: 1
maxLength: 100
role:
type: string
enum: [user, moderator, admin]
default: user
metadata:
type: object
additionalProperties: true
UpdateUserRequest:
type: object
minProperties: 1
properties:
name:
type: string
minLength: 1
maxLength: 100
status:
$ref: "#/components/schemas/UserStatus"
role:
type: string
enum: [user, moderator, admin]
metadata:
type: object
additionalProperties: true
UserListResponse:
type: object
required:
- data
- pagination
properties:
data:
type: array
items:
$ref: "#/components/schemas/User"
pagination:
$ref: "#/components/schemas/Pagination"
Pagination:
type: object
required:
- page
- limit
- total
- totalPages
properties:
page:
type: integer
minimum: 1
limit:
type: integer
minimum: 1
maximum: 100
total:
type: integer
minimum: 0
totalPages:
type: integer
minimum: 0
hasNext:
type: boolean
hasPrev:
type: boolean
Error:
type: object
required:
- code
- message
properties:
code:
type: string
description: Error code for programmatic handling
message:
type: string
description: Human-readable error message
details:
type: array
items:
type: object
properties:
field:
type: string
message:
type: string
requestId:
type: string
description: Request ID for support
parameters:
UserIdParam:
name: userId
in: path
required: true
description: User ID
schema:
type: string
format: uuid
PageParam:
name: page
in: query
description: Page number (1-based)
schema:
type: integer
minimum: 1
default: 1
LimitParam:
name: limit
in: query
description: Items per page
schema:
type: integer
minimum: 1
maximum: 100
default: 20
responses:
BadRequest:
description: Invalid request
content:
application/json:
schema:
$ref: "#/components/schemas/Error"
example:
code: VALIDATION_ERROR
message: Invalid request parameters
details:
- field: email
message: Must be a valid email address
Unauthorized:
description: Authentication required
content:
application/json:
schema:
$ref: "#/components/schemas/Error"
example:
code: UNAUTHORIZED
message: Authentication required
NotFound:
description: Resource not found
content:
application/json:
schema:
$ref: "#/components/schemas/Error"
example:
code: NOT_FOUND
message: User not found
RateLimited:
description: Too many requests
content:
application/json:
schema:
$ref: "#/components/schemas/Error"
headers:
Retry-After:
description: Seconds until rate limit resets
schema:
type: integer
X-RateLimit-Limit:
description: Request limit per window
schema:
type: integer
X-RateLimit-Remaining:
description: Remaining requests in window
schema:
type: integer
examples:
UserListExample:
value:
data:
- id: "550e8400-e29b-41d4-a716-446655440000"
email: "john@example.com"
name: "John Doe"
status: "active"
role: "user"
createdAt: "2024-01-15T10:30:00Z"
pagination:
page: 1
limit: 20
total: 1
totalPages: 1
hasNext: false
hasPrev: false
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat: JWT
description: JWT token from /auth/login
apiKey:
type: apiKey
in: header
name: X-API-Key
description: API key for service-to-service calls
security:
- bearerAuth: []
For advanced code-first generation patterns and tooling, see references/code-first-and-tooling.md:
- Template 2: Python/FastAPI — Pydantic models with
Fieldvalidation, enum types, full CRUD endpoints withresponse_modelandstatus_code, exporting the spec as JSON - Template 3: TypeScript/tsoa — Decorator-based controllers (
@Route,@Get,@Security,@Example,@Response) that generate OpenAPI from TypeScript types - Template 4: Validation & Linting — Spectral ruleset (
.spectral.yaml) with custom rules for operationId, security, naming conventions; Redocly config with MIME type enforcement and code sample generation - SDK Generation —
openapi-generator-clifor TypeScript (fetch), Python, and Go clients