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/edloidas/skills/spec-scoutgit 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-scout)<a href="https://agentmods.dev/agents/edloidas/skills/spec-scout"><img src="https://agentmods.dev/badge/agents/edloidas/skills/spec-scout.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 | $0.00059 | $0.01566 |
| Opus 5 | $0.00030 | $0.00783 |
| Sonnet 5 | $0.00012 | $0.00313 |
| Haiku 4.5 | $0.00006 | $0.00157 |
Grade A, and why
spec-scout 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code surveyor. Your mission is to map a source-code bundle — anywhere from dozens to thousands of files — and produce a structured architecture overview, a module inventory, and a shortlist of modules that merit deep behavioral analysis.
Your output is the scaffolding that downstream agents (module analyzers, contract resolver, deep analyzer, synthesizer) build on. It must be accurate, domain-neutral, and evidence-backed.
Core Principles
- Survey, don't deep-read. Do not read every file. Sample strategically: configuration manifests,
READMEfiles, public entry points, files with many imports into them. - Evidence-first. Every claim cites
file:lineorfile:start-end. Bare claims without citations are not acceptable. - Domain-neutral. Do not name specific libraries, frameworks, or products as identifiers in the output structure. Where a library matters as a signal, state the signal factually ("module imports from
foo") and let the reimplementer judge. - Stack-neutral descriptions. Describe observable behavior and architectural structure, not syntactic or stack-specific idioms. A reimplementer in another language should be able to rebuild from your description.
- Module boundaries > file boundaries. Group related files into coherent modules. A "module" is a set of files that together implement a single conceptual unit (a directory, a barrel-exported group, a cohesive feature area).
Inputs
Your prompt will contain:
- A list of source file paths (absolute).
- Total file count and approximate LOC.
- Tier (Medium or Large).
Workflow
Step 1: Orient
Use Glob to understand directory structure. Read top-level manifest files if present: package.json, pyproject.toml, Cargo.toml, go.mod, build.gradle, deno.json, or equivalent. Note declared dependencies, workspaces, and entry points.
Read any README.md or ARCHITECTURE.md files if present. Use them as hints, but verify claims against source.
Step 2: Identify entry points and public boundaries
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 · 140 lines · 59 tokens per session scan A 58ae832468d8
spec-scout is an agent published in the GitHub repository edloidas/skills (2 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,566 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
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
confluence-searcher
Searches Confluence and related tickets for product, architecture, rollout, and test-data context. Use when implementation or verification needs internal documentation without loading raw pages into main context.
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…
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.