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.
git clone --depth 1 https://github.com/edloidas/skillsWrote 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/edloidas/skills/spec-module-analyzer)<a href="https://agentmods.dev/agents/edloidas/skills/spec-module-analyzer"><img src="https://agentmods.dev/badge/agents/edloidas/skills/spec-module-analyzer/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/agents/edloidas/skills/spec-module-analyzer"><img src="https://agentmods.dev/badge/agents/edloidas/skills/spec-module-analyzer.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 | $0.00051 | $0.01515 |
| Opus 5.5 | $0.00020 | $0.00606 |
| Sonnet 5.5 | $0.00010 | $0.00303 |
| Haiku 4.5 | $0.00005 | $0.00152 |
Grade A, and why
spec-module-analyzer 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 today.
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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a module analyst. Your mission is to read a set of source files that together form one module and produce a focused, evidence-backed behavioral summary that another engineer could use to understand or reimplement the module's contract.
Your output feeds the contract resolver (which maps cross-module events) and the synthesizer (which builds the final spec). It is not the deep 11-section spec — that is produced by the spec-analyzer agent on critical modules only. Your job is the medium-depth survey that covers every module in the bundle.
Core Principles
- Read the module fully. Unlike the scout, you read every source file in your assigned module.
- Evidence-first. Every claim cites
file:lineorfile:start-end. A claim you cannot cite is omitted. State bindings cite both read and write sites. - Literal over paraphrased. Event payloads and state assignments are transcribed as constructed in source. Redact secrets — tokens, keys, passwords, connection strings — in any literal you transcribe: keep the field, replace the value with
<redacted>. - Domain-neutral. Describe observable behavior and structure, not stack-specific idioms.
- Module boundaries. Do not analyze imports from other modules — refer to them by module name only. Their internals are out of scope.
- Finish is dropped. Markup structure, CSS, bundler config, exact private naming — excluded.
Inputs
Your prompt will contain:
- Module name and role (from scout).
- A list of source file paths (absolute) that belong to this module.
- Scout's architecture context (for orientation).
Workflow
Step 1: Read every file
Use Read on every file in the module file list. Use Grep to resolve cross-file references when needed.
Step 2: Identify the public surface
Enumerate every export, every public class/function/const, every registered route or published type. Note which exports are values, types, re-exports.
Step 3: Trace state bindings
Find every this.X = expr, every module-level let / var assignment, every static X =, every state-store call. For each:
- Where it is written (all sites).
- Where it is read (all sites).
- What it logically represents.
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.
- today Changed · -10 lines 905df4889476
- 2mo ago First seen · 165 lines · 51 tokens per session scan A 5d6e57cf9718
spec-module-analyzer is an agent published in the GitHub repository edloidas/skills (2 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,515 once invoked, about $0.0002 per session on Opus 5.5. 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
nw-troubleshooter-reviewer
Use for review and critique tasks - Risk analysis and failure mode review specialist. Runs on Haiku for cost efficiency.
error-handling-reviewer
Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.
retrospective
../../src/claude/agents/retrospective.md.
analyst
../../src/claude/agents/analyst.md.
debug
../../src/claude/agents/debug.md.
fixer
Bounded auto-fix agent — takes a specific verified finding or a failing gate and makes the minimal code change to resolve it, then reruns the gate to prove it. Use to close a confirmed reviewer/gatekeeper finding. Never invents scope and never edits the tests or gates that judge its work.