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 skills/alexei-led/architect/tools-codegraphnpx skills add alexei-led/architect --skill tools-codegraphgit clone --depth 1 https://github.com/alexei-led/architectWhat 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 | $0.00107 | $0.00979 |
| Opus 5 | $0.00053 | $0.00490 |
| Sonnet 5 | $0.00021 | $0.00196 |
| Haiku 4.5 | $0.00011 | $0.00098 |
Grade A, and why
tools-codegraph 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 yesterday.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codegraph
codegraph builds a persistent graph of the codebase — symbols, references, and
call edges — that you query without re-parsing each time. It answers
graph-shaped questions ast-grep can't: what depends on this, what does a change
affect, where are the hubs and cycles.
Evidence dimensions: dependency and semantic.
When to use
Use to map observed module structure against declared modules, to find import or call cycles, high-fan-in hubs, wrong-way dependencies, and to size the blast radius of a proposed change. Build the graph during the system-map step; query it during evidence gathering.
Commands
codegraph init # set up graph store; prefer an external cache/store if supported
codegraph index # full parse → build the graph
codegraph sync # incremental update after changes
codegraph status # index health + commit it was built at
codegraph query "<expr>" # query symbols / edges
codegraph context <symbol> # neighbors of a symbol (callers, callees, refs)
codegraph affected <path> # what a change to <path> reaches (blast radius)
codegraph files <symbol> # files defining/referencing a symbol
Typical flow: init once, index, then status to confirm freshness, then
query / context / affected for evidence.
Stale-index handling
Run codegraph status before each scoring query batch. If the index commit does
not match the working tree, the graph describes an old repo:
- Run
codegraph sync(incremental) orcodegraph index(full) to refresh. - If you cannot refresh (read-only target, time budget, or no approved writable
cache), the stale graph is not evidence — record the dependency dimension
tools_failedwith reason "stale index," and do not score dependency health from it.
Evidence output
Record:
dimension: dependency or semantic.source:codegraph statusfreshness, query/context/affected command, and scope.facts: cycles, hubs, fan-in/out, callers/callees, affected paths, or confirmed absence.limits: stale index, partial language coverage, unsupported files, or failed indexing.
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.
- yesterday First seen · 99 lines · 107 tokens per session scan A c812e536f15c
tools-codegraph is a skill published in the GitHub repository alexei-led/architect (2 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 979 once invoked, about $0.0005 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 skills, from other repositories
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
map-wayfind
Decision-frontier wayfinding: build and work a durable map of open design decisions BEFORE planning, for large or foggy efforts where /map-plan would force premature decomposition. Use when a task is too big or too vague to decompose — many unknowns, tangled decisions, or "I'm not even sure what to build yet" — and…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
alphafold-database
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.