Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Eliyce/paqad-ai --skill api-doc-maintainergit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/eliyce/paqad-ai/api-doc-maintainer)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/api-doc-maintainer"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/api-doc-maintainer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/api-doc-maintainer"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/api-doc-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.00592 |
| Opus 5 | $0.00007 | $0.00296 |
| Sonnet 5 | $0.00003 | $0.00118 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade A, and why
api-doc-maintainer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Keeps per-module API docs accurate after endpoint changes by updating routes, schemas, permissions, and error references together instead of as disconnected edits.
Use This When
Use this after any implementation or design change that adds, removes, or modifies endpoints, payloads, auth rules, or API error behavior.
Inputs
- Read the module API docs first:
api/endpoints.md,api/schemas.md, andapi/error-codes.mdwhen they exist. - Read the changed controllers, routes, handlers, or generated endpoint inventory for the module.
- Read
references/api-entry-requirements.mdbefore editing the docs.
Procedure
- Run
scripts/find-api-docs.shto enumerate the canonical per-module API doc paths that already exist. - Identify endpoints whose request, response, auth, permission, or error behavior changed.
- Update or add endpoint entries using
assets/endpoint-entry.template.md— fill every required field; never ship a partial entry. - Update schemas and error codes in the same pass; cross-link new errors to the module error catalog.
- Verify documented auth, versioning, and rate-limit statements still match implementation.
- Format the report per
assets/output.template.mdand validate withscripts/lint-output.sh.
Output Contract
- Match
assets/output.template.md:## Updated API Docs(one bullet per file with backticked path) and## Coverage Gaps. - Output must pass
scripts/lint-output.sh(exit 0). - Required-but-missing endpoint details belong under
Coverage Gaps, never as guessed entries.
Escalate / Stop Conditions
- Ask when the implementation does not expose enough evidence to confirm auth, permissions, or payload shape.
- Warn when code and existing docs disagree on a breaking API behavior.
- Do not create placeholder endpoint entries with missing required fields.
Resources
references/api-entry-requirements.mdscripts/find-api-docs.shscripts/lint-output.shassets/output.template.mdassets/endpoint-entry.template.mdruntime/capabilities/coding/stacks/laravel/references/tools/testing.mdagents/openai.yaml
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 69 lines · 14 tokens per session scan A 6495c62221dd
api-doc-maintainer is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 592 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
api-design
A guide to designing web APIs—the interfaces that let software systems exchange data—using REST, gRPC, and GraphQL patterns.
latency-analysis
Analyze endpoint latency trends using historical check data from memory. Detects slow degradation, spikes vs sustained issues, and calculates baseline deviations.
response-validation
Validate API response structure and content. Detects schema drift, unexpected null values, and abnormal response sizes.
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
api-contract-testing
Curl-based HTTP endpoint probing and response validation. Tests status codes, response bodies, headers, and schema conformance against expected contracts.
Architecture Designer
Designs system-level structures including modules, services, data flow, and scaling strategy before implementation begins.