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/tk-logl/sentinel/file-headersnpx skills add tk-logl/sentinel --skill file-headersgit clone --depth 1 https://github.com/tk-logl/sentinelWhat 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 | $0.00042 | $0.01077 |
| Opus 5 | $0.00021 | $0.00539 |
| Sonnet 5 | $0.00008 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
file-headers scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Verify: pytest tests/test_app.py -x && curl -s localhost:8000/health | jq .status How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Header System
Short, structured comments at the top of key source files that capture critical context.
Why Headers Exist
When AI assistants (or developers) edit a file, they often don't know:
- What this file's actual role is in the system
- Which other files MUST change together with it
- What invariants must never be broken
- How to verify changes work
Headers solve this in 5-12 lines, saving investigation time and preventing mistakes.
When to Add Headers
- Files over 200 lines (configurable in sentinel.json:
header_threshold_lines) - Files that are frequently co-modified with others
- Files containing critical business logic or security code
- Entry points (main.py, app.ts, index.js)
Header Format
Python
"""
app.py — Main application server with API routing and request handling.
Co-modify: services/auth.py, services/handler.py, utils/response.py
Invariants:
- All endpoints must validate auth before processing
- Responses must use consistent error format
- Database connections must be properly closed on error
Verify: pytest tests/test_app.py -x && curl -s localhost:8000/health | jq .status
"""
TypeScript/JavaScript
/**
* App.tsx — Root application component with routing and theme management.
*
* Co-modify: stores/authStore.ts, services/api.ts, components/layout/MainLayout.tsx
* Invariants:
* - AuthProvider must wrap all routes (no unauthenticated renders)
* - Theme CSS variables must be set before first paint (no flash)
* - Error boundary must catch all route-level errors
* Verify: npm run build && npm run test -- --run
*/
Go
// server.go — HTTP server with middleware chain and graceful shutdown.
//
// Co-modify: middleware/auth.go, handlers/api.go, config/config.go
// Invariants:
// - Shutdown must drain all active connections (30s timeout)
// - Auth middleware must run before any handler (middleware order matters)
// - Config must be loaded before server starts (no lazy init)
// Verify: go test ./... && go build ./cmd/server
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 · 138 lines · 42 tokens per session scan A 505029237f8a
file-headers is a skill published in the GitHub repository tk-logl/sentinel (4 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 1,077 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.