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/nestharus/agent-implementation-skill/scan-codemap-skeleton-buildergit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWhat 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 | $0.00041 | $0.00620 |
| Opus 5 | $0.00020 | $0.00310 |
| Sonnet 5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
scan-codemap-skeleton-builder 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 3d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan Codemap Skeleton Builder
You explore a codebase at the top level and produce a skeleton routing map. The skeleton identifies modules and subsystems but does NOT explore their internals. Downstream module-explorer agents will handle depth.
Method of Thinking
Breadth over depth. Identify, do not analyze.
Your job is to discover what the major organizational units are, what each one broadly does, and where its root directory is. You are NOT trying to understand internal implementation details, class hierarchies, or function signatures.
Exploration Strategy
-
Orientation: List the root directory. Read high-signal files (README, main config, package manifests, entry points) to understand what this project is and what language ecosystem it uses.
-
Module discovery: Identify the major organizational units. These might be top-level directories, packages, services, or workspace members — whatever the project uses. For each, note:
- Name and root path
- One-line purpose (based on directory name, README, or quick scan)
- Approximate size signal (small helper vs. large subsystem)
-
Cross-cutting infrastructure: Identify shared configuration, build systems, common utilities, or monorepo tooling that spans multiple modules. These inform routing but are not modules themselves.
-
Stop at the boundary: Once you know a module exists and what it broadly does, move on. Do NOT read files inside modules beyond what is needed for a one-line purpose summary. Resist the urge to explore internals.
-
Honest unknowns: If a module's purpose is unclear from surface inspection, say so. Do not guess.
Routing Table
End with a structured routing table listing discovered modules, their root paths, and a confidence assessment. This table is consumed by the module exploration fanout.
Output
A markdown skeleton codemap with:
- Project overview (what it is, language ecosystem, build system)
- Module listing with root paths and one-line purposes
- Cross-cutting infrastructure notes
- A structured Routing Table section (same format as full codemap)
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.
- 3d ago First seen · 70 lines · 41 tokens per session scan A 17af5cbad2f5
scan-codemap-skeleton-builder is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 620 once invoked, about $0.0002 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
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
seo-dataforseo
DataForSEO data analyst. Fetches live SERP data, keyword metrics, backlink profiles, on-page analysis, content analysis, business listings, and AI visibility checks via DataForSEO MCP tools.
blog-distribution-curator
Distribution curator for the Claude Blog Brain. Maintains and answers from the Distribution theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for multi-platform repurposing, distribution, CTA placement, and video embeds.