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/di-sukharev/code-scout-skill/code-scoutnpx skills add di-sukharev/code-scout-skill --skill code-scoutgit clone --depth 1 https://github.com/di-sukharev/code-scout-skillWrote 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/di-sukharev/code-scout-skill/code-scout)<a href="https://agentmods.dev/skills/di-sukharev/code-scout-skill/code-scout"><img src="https://agentmods.dev/badge/skills/di-sukharev/code-scout-skill/code-scout.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 | $0.00135 | $0.02454 |
| Opus 5 | $0.00068 | $0.01227 |
| Sonnet 5 | $0.00027 | $0.00491 |
| Haiku 4.5 | $0.00014 | $0.00245 |
Grade A, and why
code-scout 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Scout
Purpose
Run one bounded discovery pass before the primary agent designs or edits a non-trivial code change. Keep repository-search noise out of the primary conversation by returning a small, verifiable evidence map instead of a search transcript.
Keep ownership with the primary agent. The scout identifies likely owners, couplings, tests, flows, and constraints; it does not choose the fix, edit files, or replace local verification of its result.
Apply the Eligibility Gate
Run the scout only when all of these are true:
- The task requires repository discovery.
- The work is non-trivial or crosses files, modules, layers, contracts, or tests.
- The owning files, entry points, important symbols, or closest tests are not already sufficiently explicit.
- A fresh sub-agent can be started without inheriting the parent conversation.
Skip the scout when any of these are true:
- The task is documentation-only.
- The requested edit already names the exact file and symbol and nearby inspection is enough.
- The change is an obvious local copy, style, or similarly bounded edit.
- The user asks only for an answer that needs no code search.
- The user forbids delegation.
- This skill already produced a verified map for the same stable task scope and repository state.
- The repository or fresh-agent capability is unavailable.
An explicit $code-scout invocation overrides the ordinary cost/benefit
heuristic, but not a user prohibition, missing capability, or safety constraint.
Run exactly one scout at a time. Do not turn discovery into a review loop.
Prepare the Scout
- Normalize the task into one implementation goal and one observable primary signal.
- Resolve the absolute Git repository root.
- Identify only the repository guidance the scout needs to read, such as
AGENTS.md, a rootREADME.md,CONTRIBUTING.md, and directly relevant architecture documents. Pass filenames and task constraints, not summaries of the expected answer. - Resolve
scripts/repository_fingerprint.pyrelative to thisSKILL.md. - Run the fingerprint script against the repository before spawning:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 246 lines · 135 tokens per session scan A 2e7a4410df78
code-scout is a skill published in the GitHub repository di-sukharev/code-scout-skill (5 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 2,454 once invoked, about $0.0007 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…