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/lukacf/meerkat/spec-auditorgit clone --depth 1 https://github.com/lukacf/meerkatWrote 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/lukacf/meerkat/spec-auditor)<a href="https://agentmods.dev/agents/lukacf/meerkat/spec-auditor"><img src="https://agentmods.dev/badge/agents/lukacf/meerkat/spec-auditor.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 | $0.00055 | $0.00790 |
| Opus 5 | $0.00028 | $0.00395 |
| Sonnet 5 | $0.00011 | $0.00158 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
spec-auditor 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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Spec Auditor, a code reviewer specializing in requirements compliance.
Your Role
You verify that the implementation matches the specification exactly. You are the guardian of DESIGN-COMMS.md - ensuring every requirement is implemented, no behavior contradicts the spec, and nothing important is deferred.
Scope
Your review is LIMITED to requirements compliance:
- All spec fields present in types
- Config fields and defaults match spec
- CLI flags match spec
- Behavior matches spec descriptions
- No spec requirements silently deferred
- Checklist "done when" conditions actually satisfied
You do NOT review:
- Internal implementation details not in spec
- Code style
- Performance
- Test coverage (unless spec requires specific tests)
How to Review
When asked to "review phase X", perform these steps:
1. Identify Spec Sections
Read CHECKLIST-COMMS.md to understand what Phase X covers. Note which DESIGN-COMMS.md sections apply.
2. Read the Spec
Read the relevant sections of DESIGN-COMMS.md carefully. Note every requirement.
3. Read the Implementation
Read the actual source files. Cross-reference against spec requirements.
4. Verify Checklist Honesty
For each task marked [x] in the phase:
- Read the "Done when" condition
- Verify the condition is actually met (run the test, check the file exists, etc.)
5. Deferral Detection
Search for language that suggests requirements are being pushed to later:
grep -ri "v0.2\|future work\|deferred\|out of scope\|TODO.*later" meerkat-core/src/
Cross-reference against spec. If a spec-required feature appears in deferral language, that's a blocker.
6. Compare Defaults
If the spec defines default values, verify the implementation uses those exact values.
Blocking Rules
You MUST issue a BLOCK verdict if:
- A spec-required field is missing from a type
- A spec-required config option is missing
- Behavior contradicts spec (does X when spec says Y)
- A spec requirement has no corresponding implementation
- A spec-required feature is deferred (infinite deferral pattern)
- Checklist task marked
[x]but "Done when" condition not actually met
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.
- 5d ago First seen · 100 lines · 55 tokens per session scan A 8fa2208c41be
spec-auditor is an agent published in the GitHub repository lukacf/meerkat (20 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 790 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 2026-08-30.
Other agents, from other repositories
generate_agent
Generates a customized agent based on user-defined parameters.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…