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/roarista/awesome-harness/codebase-firstnpx skills add roarista/awesome-harness --skill codebase-firstgit clone --depth 1 https://github.com/roarista/awesome-harnessWhat 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 | $0.00055 | $0.00443 |
| Opus 5 | $0.00028 | $0.00221 |
| Sonnet 5 | $0.00011 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
codebase-first 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.
What it actually says
codebase-first
Run before non-trivial code changes. The output is a compact proof of the smallest missing piece, not a broad repository tour.
Discovery ladder
Stop at the first rung that fully satisfies the goal:
- Need: does current behavior already satisfy the request?
- Front door: read the compact project router, current resume card, and relevant authority.
- Map: use the injected code map and Graphify for structure/reach; use Semgrep for complete AST occurrences and
rgfor literals/history. - Native/platform: check whether the runtime or framework already provides it.
- Installed dependency: inspect the manifest and live API.
- Nearby workflow: inspect the closest active implementation and its callers.
- Boundary/blast radius: identify consumers, errors, persistence, permissions, and files affected.
- Probe: run the smallest read-only check that distinguishes competing assumptions.
- Gap: name only what remains missing.
For every plausible candidate, record REUSE, ADAPT, or REJECT with a file:line or command-output anchor. Do not claim absence from a map alone.
Gate
STOP: current/native/dependency behavior covers the goal, or implementation would require an unresolved authority decision.PLAN: integration crosses multiple boundaries or changes a schema, public API, dependency, destructive migration, or authority.BUILD: candidates, consumers, boundaries, residual gap, and pre-code verification are all explicit.
For localized work, carry the evidence inline. Otherwise write .scratch/discovery/<slug>.md with goal, constraints, source anchors, candidate verdicts, boundary map, empirical probe, residual gap, gate, and verification.
On BUILD, pass only the residual gap and evidence anchors to code-decompose. On STOP or PLAN, write no production 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.
- 2d ago First seen · 35 lines · 55 tokens per session scan A 0ec75740468e
codebase-first is a skill published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 6d ago), licensed MIT. It adds 55 tokens to every session and 443 once invoked, about $0.0003 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…