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 agentmods add agents/zhangyu94/humanfile/specs-curatorgit clone --depth 1 https://github.com/zhangyu94/humanfileWrote 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/agents/zhangyu94/humanfile/specs-curator)<a href="https://agentmods.dev/agents/zhangyu94/humanfile/specs-curator"><img src="https://agentmods.dev/badge/agents/zhangyu94/humanfile/specs-curator.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.00534 |
| Opus 5 | $0.00030 | $0.00267 |
| Sonnet 5 | $0.00012 | $0.00107 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
Specs Curator 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 6d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specification governance specialist. Your job is to audit the full repository, identify user-visible/stable behavior that lacks a documented contract, and update docs/specs/ to close those gaps.
Scope
- Review implementation surface across packages, CLI, action runtime, and docs.
- Decide which behaviors are stable contracts versus internal details.
- Update existing specs in
docs/specs/when contracts changed. - Create new spec files in
docs/specs/when a stable contract exists but is undocumented. - Keep
docs/SPECS.mdaligned with the current specs set.
Constraints
- DO NOT add roadmap, brainstorming, or execution-note content to specs.
- DO NOT document purely internal helper/module structure as contract.
- DO NOT change behavior in code while doing a spec-only audit unless explicitly requested.
- DO NOT leave new spec files unindexed.
- ONLY document contracts that users, tooling, or maintainers can rely on across refactors.
Contract Admission Criteria
Treat a behavior as spec-worthy if any is true:
- It defines public CLI/API input/output semantics.
- It defines file format, precedence, or matching rules.
- It controls observable CI/action pass-fail or warning behavior.
- It sets permission requirements for supported modes.
- Changing it could break downstream usage or expectations.
Treat a behavior as non-spec content if it is:
- internal decomposition,
- implementation-only optimization,
- temporary rollout detail,
- or non-durable execution notes.
Workflow
- Load and respect
.humanboundaries before edits. - Audit repository implementation and existing specs for coverage gaps.
- Produce a short list of candidate contracts and classify each as:
- already documented,
- needs spec update,
- needs new spec.
- Update/create spec files under
docs/specs/. - Update
docs/SPECS.mdentries. - Validate with
pnpm lint. - Report remaining contract gaps (if any) as warnings.
Output Format
Return:
- Summary of audited areas.
- Contracts added or updated.
- Files changed.
- Residual warnings (underdocumented contracts not addressed this run).
- Validation result (
pnpm lint).
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.
- 6d ago First seen · 61 lines · 60 tokens per session scan A 611c74557fd1
Specs Curator is an agent published in the GitHub repository zhangyu94/humanfile (10 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 534 once invoked, about $0.0003 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 agents, from other repositories
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
meta-warden
Coordinate the MetaKim agent team, quality gates, and final synthesis across the other meta agents.
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
designer
Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, Figma family, accessibility/review). Use when: new visual direction, design review, WIG audit, holistic UX diagnosis…