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/sylphxai/coderag/agents-mdgit clone --depth 1 https://github.com/SylphxAI/coderagWhat 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 | $0.00401 | $0.00401 |
| Opus 5 | $0.00200 | $0.00200 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
coderag 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 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- smart-reader-mcp AGENTS.md — 89% identical, 7 lines differ
- image-reader-mcp AGENTS.md — 89% identical, 6 lines differ
- video-reader-mcp AGENTS.md — 86% identical, 8 lines differ
What it actually says
coderag — local agent notes only
Static engineering and delivery standards load from the active Skills runtime (SylphxAI/skills is binding instruction SSOT). Doctrine and Mission Control are retired historical lineage and must not be loaded as current instruction authority.
Local truth: PROJECT.md, .doctrine/project.json when present.
Boundary hazards
- Never commit secrets, tokens,
.envfiles, or credentials.
Local commands
bun run typecheckbun run testbun run lintbun run buildcargo test --workspace- Prefer the narrowest affected check before full workspace runs.
- Report layers honestly: local diff · trunk FF · deploy · prod proof (do not collapse).
Validation notes
- Prefer the narrowest affected check before full workspace runs.
- Report layers honestly: local diff · trunk FF · deploy · prod proof (do not collapse).
Backend false-authority fence
Work: wi_01KYFN6993PMG8WD00Q51AE231
If this repository has completed a Rust backend cutover:
- Production backend behavior authority is the Rust crate/binary/service path declared in
sylphx.toml/ deploy manifests / packagebinnative path / Docker ENTRYPOINT. - Residual TypeScript service trees or alternate TS engines are not product authority unless explicitly proven still on the live path.
- Do not "fix production" by editing residual TypeScript and assuming deploy/runtime will pick it up.
- Prefer deleting residual TS backend trees after Rust sole proof; keep history in Git.
- Intentional TypeScript frontends, npm packaging wrappers, and native-binding surfaces may remain.
Repo-specific note
Rust crates own retrieval/MCP server core; residual TS packages are not production authority without publish proof.
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 · 44 lines · 401 tokens per session scan A 21a6cd6f565d
coderag AGENTS.md is an instructions file published in the GitHub repository SylphxAI/coderag (12 stars, last pushed 7d ago), licensed MIT. It adds 401 tokens to every session, about $0.0020 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 2026-08-30.
Other instructions, from other repositories
mcp-docs-ask AGENTS.md
AGENTS.md instructions for alyiox/mcp-docs-ask, covering agent instructions, commit messages, header, body and release tags.
mcp-docs-ask CLAUDE.md
Claude Code instructions for alyiox/mcp-docs-ask, a project described as: Local RAG MCP for markdown docs — retrieval with citations from a local path or git URL (no answer LLM).
open-codebase-index AGENTS.md
Instructions for Helweg/open-codebase-index, covering agents.md - ai agent guidelines for open-codebase-index, build, test, and lint, run a single test, equivalent low-level command and architecture and file structure.
honcho CLAUDE.md
Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.
gno AGENTS.md
Instructions for gmickel/gno, covering knowledge cutoff warning, apis - bun first!, must use bun, acceptable node:\ (no bun equivalent) and testing.
coco-search CLAUDE.md
Instructions for VioletCranberry/coco-search, covering project instructions, project overview, tool routing (mandatory), development setup and prerequisites: docker, uv (python package manager).