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/nxtsoft/cgraph/cgraph-enrichnpx skills add Nxtsoft/CGraph --skill cgraph-enrichgit clone --depth 1 https://github.com/Nxtsoft/CGraphWhat 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 | $0.00128 | $0.01435 |
| Opus 5 | $0.00064 | $0.00718 |
| Sonnet 5 | $0.00026 | $0.00287 |
| Haiku 4.5 | $0.00013 | $0.00144 |
Grade A, and why
cgraph-enrich 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 2d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cgraph-enrich
cgraph extracts code structure deterministically, but documentation, design notes, and other prose only enter the graph as host-authored semantic fragments. This skill is the loop that produces them. The native tool owns chunk planning, fragment validation, content-hash caching, and graph mutation; you (the model) own reading each chunk and authoring the fragment. No model logic lives in the binary.
The loop
Run from the project root. Repeat until the plan reports 0 input(s).
-
Plan —
cgraph enrich-plan --root . --out cgraph-outWritescgraph-out/semantic-drop/plan.json, listing only uncached or stale chunks. Each chunk hasinputs[].pathand afragmentfield — the exact filename to drop. Already-enriched files are skipped via the content-hash cache. Fragment names are offset past the fragments already in the drop dir, so the directory accumulates across passes and a new pass never overwrites an earlier one — always read the fresh plan and use the names it gives. -
Author — for each chunk in
plan.json:- Read every file in
inputs[].path. - Author ONE fragment capturing the chunk's concepts and how they relate to each other and to the code (see Fragment shape below).
- Write it atomically to
cgraph-out/semantic-drop/<chunk.fragment>— the filename from the chunk'sfragmentfield, never a name you pick yourself. Write a temp file in that directory, then rename it into place. Do not reuse or overwrite an existing fragment file.
- Read every file in
-
Merge — one of:
- Batch:
cgraph enrich-ingest --root . --out cgraph-outvalidates every dropped fragment, merges the valid ones, updates the cache, and re-exports. - Live: if a daemon is running (
graph_status), dropping the file is enough — the watcher validates and merges it into the live snapshot within ~200ms.
- Batch:
-
Verify & repeat — re-run
enrich-plan. Enriched files are now cache hits and drop out.graph_statusshowsenrichment_pendingfalling andnode_countrising. Loop until pending is 0. Malformed fragments are rejected and leave the graph unchanged (enrichment_state: failed); fix and re-drop the samechunk_<index>.json.
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.
- 2d ago First seen · 106 lines · 128 tokens per session scan A d200023277d9
cgraph-enrich is a skill published in the GitHub repository Nxtsoft/CGraph (2 stars, last pushed 5d ago), licensed MIT. It adds 128 tokens to every session and 1,435 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.