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/leifericf/agentic-sdk/gather-module-contextnpx skills add leifericf/agentic-sdk --skill gather-module-contextgit clone --depth 1 https://github.com/leifericf/agentic-sdkWrote 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/skills/leifericf/agentic-sdk/gather-module-context)<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/gather-module-context"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/gather-module-context.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 | $0.00030 | $0.00701 |
| Opus 5 | $0.00015 | $0.00351 |
| Sonnet 5 | $0.00006 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
gather-module-context 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gather-module-context
Produce the few hundred tokens a dispatched agent needs instead of rediscovering the module. Build from disk, not memory. The orchestrator pastes the return value into its dispatch prompts. Nothing is written to disk.
Procedure
Sources, in order:
- The module map. The descriptor's
:architecture :modulesrow for the module: its responsibility, the files it owns, the dependency directions that touch it. Detailed contracts live inreferences/architecture.md. Pre-build, the row is the module definition until code lands; markRECENT: pre-build, no history yetandTESTS: pre-build, no tests yet. ls <module-dir>. The actual files, if the directory exists. The map can lag the code; note any drift. If the directory does not exist yet, skip this source and noteSIZES: pre-build, dir not yet created.- Owning tests. The test namespace or file that exercises the module, and the round-trip integration test if it sits on the native edge. Pre-build: empty; say so.
jj logover the module path (orjj log -rlimited to recent commits touching the dir). What changed recently and why; flags active work and fresh bug history. Pre-build: empty; sayno history yet.docs/adr/README.md. The decision index, if it exists (it is created byrecord-decisionwhen the first ADR lands; do not create it here). Quote any row whose title touches the module or its idioms, so dispatched agents know what is deliberate before they review or edit.- Sizes.
wc -lon existing files to surface any approaching the soft limits (about 800 lines per file, about 200 per function). A file near the limit is a factoring finding waiting to happen. Pre-build: nothing to measure.
Brief format (keep under about 40 lines):
MODULE <dir>
RESPONSIBILITY: <one line per file, from the map and the code>
BOUNDARY: may include <...>; must NOT touch <other modules, the pure core from the shell, the public API from non-owning modules>
TESTS: <test files> (run: the owning lane)
RECENT: <3-5 one-line commits, or "no history yet">
SIZES: <any file or function near soft limits>
NOTES: <gotchas: native handle lifetimes, store transaction shapes, real-time constraints, validation layers, platform splits, generated files>
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 · 67 lines · 30 tokens per session scan A 08399ce6a420
gather-module-context is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 701 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 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…