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 instructions/timohaa/scopewalker-mcp/agents-mdgit clone --depth 1 https://github.com/timohaa/scopewalker-mcpWrote 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/timohaa/scopewalker-mcp/agents-md)<a href="https://agentmods.dev/instructions/timohaa/scopewalker-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/timohaa/scopewalker-mcp/agents-md.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 5.1 | $0.00797 | $0.00797 |
| Opus 5 | $0.00398 | $0.00398 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
scopewalker-mcp AGENTS.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 5d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
What
MCP server providing codebase analysis tools for AI assistants. It is a thin orchestration layer over external parsing, file discovery, and line counting via tokei.
How
npm run build # Build
npm run check # Version sync + lint + typecheck (run before committing)
npm run test # Run tests
npm run test:coverage # Tests with coverage
Use the project's own MCP tools to understand and validate code. Run check_thresholds before committing.
If LSP tools are available in your session, prefer them (workspaceSymbol, findReferences, goToDefinition, hover) over Grep/Read for code navigation; otherwise use Grep for text/pattern searches.
Behavior
- For ambiguous requests, sketch a short plan and state assumptions and tradeoffs before editing.
- Write the minimum code that solves the problem. Avoid speculative abstractions, drive-by renames, and unrelated cleanup.
- Define a success criterion before starting and loop until it passes. Verify tool output with the tool itself or its tests;
npm run checkalone is insufficient. - Pass every target file to one command (
npx vitest run a.test.ts b.test.ts,npx markdownlint f1 f2, or onegrep -nEacross all files). - Never create
_enhanced,_v2, or_newduplicate file variants; edit the original file.
Reference Docs
- TOOLS.md: tool reference
- docs/: detailed tool documentation; docs/known-bugs.md lists verified defects and gaps, check it before chasing unexpected tool output
.claude/skills/create-tool,.claude/skills/create-test: workflows and code examples for adding tools/tests/polish,/review-changes: quality-pipeline slash commands (see.claude/skills/for the rest).claude/agents/: specialized agents for standards, testing, docs, and code-quality enforcement (see directory for the full list)
Writing Style
Applies to chat responses, commit messages, PR descriptions, and docs. Ban the rhetorical move, not just the phrase — restating it in new words is still banned.
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.
- 5d ago First seen · 55 lines · 797 tokens per session scan A 4cb5a2071074
scopewalker-mcp AGENTS.md is an instructions file published in the GitHub repository timohaa/scopewalker-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 797 tokens to every session, about $0.0040 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
chunkhound AGENTS.md
AGENTS.md instructions for chunkhound/chunkhound, covering chunkhound llm context, projectidentity, modificationrules, keycommands and development.
tree-sitter-analyzer CLAUDE.md
Claude Code instructions for aimasteracc/tree-sitter-analyzer, covering ruflo — claude code configuration, rules, test quality rules — locked (2026-06-28), t-1: no new test files for existing plugins (blocker) and t-2: no weak assertions — ratchet-enforced (blocker).
tree-sitter-analyzer AGENTS.md
AGENTS.md instructions for aimasteracc/tree-sitter-analyzer, covering agent instructions, codemap index, test runtime contract, ci test tier contract and agent dogfood feedback loop.
codegraph AGENTS.md
AGENTS.md instructions for lzehrung/codegraph, covering agent directives, general and path, cache, and review safety.
flyto-indexer AGENTS.md
AGENTS.md instructions for flytohub/flyto-indexer, covering agent rules, gate remediation loop, flyto2 project memory contract and flyto2 frontend quality gate.
flyto-indexer CLAUDE.md
Claude Code instructions for flytohub/flyto-indexer, covering claude notes, cross-agent handoff, shared code intelligence, code intelligence (flyto-indexer) and first-time setup.