Borrowing it
Nothing to install: this file belongs to costajohnt/oss-scout. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/costajohnt/oss-scout/main/CLAUDE.mdgit clone --depth 1 https://github.com/costajohnt/oss-scoutWrote 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/instructions/costajohnt/oss-scout/claude-md)<a href="https://agentmods.dev/instructions/costajohnt/oss-scout/claude-md"><img src="https://agentmods.dev/badge/instructions/costajohnt/oss-scout/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/costajohnt/oss-scout/claude-md"><img src="https://agentmods.dev/badge/instructions/costajohnt/oss-scout/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01875 | $0.01875 |
| Opus 5 | $0.00937 | $0.00937 |
| Sonnet 5 | $0.00375 | $0.00375 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
oss-scout CLAUDE.md 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 8d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
oss-scout is a standalone tool for finding open source issues personalized to your contribution history. Ships as CLI, library, MCP server, and Claude Code plugin. Published as @oss-scout/core and @oss-scout/mcp on npm.
Architecture
pnpm monorepo with two packages:
-
packages/core(@oss-scout/core) — Library + CLI. Multi-strategy search engine, issue vetting, viability scoring, and theOssScoutpublic API class. -
packages/mcp-server(@oss-scout/mcp) — MCP server exposing search, scout-features, vet, skip, config, config-set, and sync tools plus scout:// resources.
Key Design Decisions
- No singletons in public API.
OssScoutaccepts config via constructor injection. ImplementsScoutStateReaderto bridge state with the search engine. - Two persistence modes:
'gist'(standalone, state in private GitHub gist) and'provided'(library, caller provides state — used by OSS Autopilot). - Extracted from OSS Autopilot. Search modules refactored to remove
StateManagersingleton. OSS Autopilot imports@oss-scout/coreas a dependency. - 4-phase search with configurable strategy selection (merged, starred, broad, maintained).
- Error strategy: Auth/rate-limit errors propagate. Cache/filesystem errors degrade gracefully with warn logging. Documented in errors.ts.
File Structure
packages/core/src/
├── index.ts # Public API exports
├── scout.ts # OssScout class + createScout() factory
├── cli.ts # Commander CLI (10 top-level commands)
├── commands/ # CLI subcommands
│ ├── setup.ts # Interactive first-run configuration
│ ├── config.ts # View/update preferences
│ ├── search.ts # Multi-strategy search with result persistence
│ ├── features.ts # Feature opportunities in anchor repos
│ ├── sync.ts # Reconcile tracked open PRs (merged/closed)
│ ├── vet.ts # Single issue vetting
│ ├── vet-list.ts # Batch re-vetting of saved results
│ ├── skip.ts # Manage the skip list
│ ├── results.ts # View/clear saved search results
│ ├── command-scout.ts # Build a scout honoring the persistence preference
│ ├── with-scout.ts # Shared create/persist scaffolding for commands
│ └── validation.ts # URL validation helpers
├── core/ # Domain logic
│ ├── schemas.ts # Zod schemas for ScoutState, ScoutPreferences
│ ├── types.ts # Ephemeral types, config interfaces
│ ├── issue-discovery.ts # 4 extracted phase functions + orchestrator
│ ├── issue-vetting.ts # Parallel vetting pipeline + ScoutStateReader/Writer
│ ├── issue-eligibility.ts # PR existence, claim detection, requirements
│ ├── issue-scoring.ts # Viability scoring (pure functions, 0-100)
│ ├── issue-filtering.ts # Spam detection, doc-only filtering
│ ├── anti-llm-policy.ts # Detect repos with anti-AI contribution policies
│ ├── feature-discovery.ts # `scout features` anchor + broad discovery
│ ├── personalization.ts # preferLanguages/preferRepos sort boosts + diversity
│ ├── linked-pr.ts # Stalled linked-PR detection (revive opportunities)
│ ├── roadmap.ts # ROADMAP.md issue-reference scraping
│ ├── slm-triage.ts # Optional Ollama SLM pre-triage during vetting
│ ├── preference-fields.ts # Shared config-set field map (CLI + MCP)
│ ├── search-phases.ts # Search helpers, caching, batched search
│ ├── search-budget.ts # Rate limit management (30 req/min sliding window)
│ ├── issue-graphql.ts # GraphQL broad search + batched merged-PR prefetch
│ ├── repo-health.ts # Project health checks, CONTRIBUTING.md parsing
│ ├── probe-repo-file.ts # Cheap existence probes for repo files
│ ├── category-mapping.ts # Project categories → GitHub topics
│ ├── github.ts # Throttled Octokit client
│ ├── http-cache.ts # ETag response caching, in-flight deduplication
│ ├── gist-state-store.ts # Gist-backed persistence with conflict resolution
│ ├── local-state.ts # Local file persistence (~/.oss-scout/state.json)
│ ├── bootstrap.ts # First-run: fetch starred repos + PR history
│ ├── utils.ts # URL parsing, token detection, extractRepoFromUrl
│ ├── logger.ts # Debug/info/warn logger (stderr)
│ ├── errors.ts # Error hierarchy + strategy documentation
│ └── pagination.ts # Auto-pagination helper
├── formatters/
│ ├── json.ts # JSON output formatter (--json envelope)
│ ├── human.ts # Human-readable terminal output
│ └── markdown.ts # Markdown output (results --markdown; used by action.yml)
├── e2e/
│ └── search-flow.test.ts # End-to-end search flow (only Octokit mocked)
└── eval/ # Vet eval suite (eval:vet scripts; excluded from dist)
packages/mcp-server/src/
├── index.ts # Library entry: createServer wiring (side-effect free)
├── bin.ts # Stdio executable entry point
├── tools.ts # 7 tools: search, scout-features, vet, skip, config, config-set, sync
└── resources.ts # 3 resources: scout://config, results, scores
Plugin (repo root):
├── commands/scout.md, scout-setup.md
├── agents/issue-scout.md, repo-evaluator.md
├── skills/oss-search/SKILL.md
├── hooks/ # hooks.json + session-start, git guard, auto-format
├── .claude-plugin/ # plugin.json, marketplace.json
├── action.yml # Composite GitHub Action (scheduled digest issue)
└── examples/ # Example workflows (weekly digest)
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.
- 8d ago First seen · 135 lines · 1,875 tokens per session scan A 1e4c01d675b1
oss-scout CLAUDE.md is an instructions file published in the GitHub repository costajohnt/oss-scout (1 stars, last pushed 25d ago), licensed MIT. It adds 1,875 tokens to every session, about $0.0094 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.