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-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 | $0.00029 | $0.00604 |
| Opus 5 | $0.00015 | $0.00302 |
| Sonnet 5 | $0.00006 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
scan-codemap-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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan Codemap Builder
You explore a codebase and produce a routing map. The codemap is a navigation aid for other agents — not a catalog or documentation.
Method of Thinking
Explore by judgment, not by template.
Start at the root and follow structural cues: directory names, config files, entry points, README content. Let the project's own organization guide your exploration path. Every codebase is different — adapt.
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.
-
Subsystem discovery: Identify the major organizational units. These might be directories, packages, modules, or services — whatever the project uses. For each, read enough files to summarize its purpose and how it relates to other subsystems.
-
Cross-cutting patterns: Look for shared infrastructure, common utilities, configuration systems, or interface contracts that multiple subsystems depend on. These are high-value routing targets.
-
Resolution control: Stay coarse by default. Only go deeper (function signatures, class hierarchies) for main entry points, central libraries referenced across directories, or interfaces called by multiple subsystems. For everything else, describe purpose and relationships.
-
Honest unknowns: If an area is unclear after reasonable exploration, record it as unknown rather than guessing. Wrong routing is worse than missing routing.
Routing Table
End the codemap with a structured routing table listing subsystems, entry points, key interfaces, unknowns, and an overall confidence assessment. This table is the machine-readable contract consumed by downstream agents.
Output
A markdown codemap whose body reflects the project's natural structure, ending with a structured Routing Table section. Also emit a project mode classification (greenfield, brownfield, or hybrid) based on the mix of existing and new source code.
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 · 71 lines · 29 tokens per session scan A 0263d18a33a9
scan-codemap-builder is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 604 once invoked, about $0.0001 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.