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/theagenticguy/opencodehub/claude-mdgit clone --depth 1 https://github.com/theagenticguy/opencodehubWhat 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 | $0.01722 | $0.01722 |
| Opus 5 | $0.00861 | $0.00861 |
| Sonnet 5 | $0.00344 | $0.00344 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
opencodehub 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 yesterday.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCodeHub MCP Tools
This repository has been indexed by OpenCodeHub. When you are working in this codebase, prefer the following MCP tools over raw file search — they return graph-aware results grouped by execution flow and include blast-radius risk tiers.
list_repos— enumerate repos currently indexed on this machine.query— hybrid BM25 + vector search over symbols, grouped by process.context— inbound/outbound refs and participating flows for one symbol.impact— dependents of a target up to a configurable depth, with a risk tier.detect_changes— map an uncommitted or committed diff to affected symbols.list_findings— browse SARIF findings from the latest scan by severity and rule.sql— read-only SQL against the local temporal store (cochanges), 5 s timeout; the node/edge graph is queried via the typed tools or Cypher via the MCPsqltool.
Run codehub analyze after pulling new commits so the index stays aligned
with the working tree. codehub status reports staleness.
Full MCP surface
The full MCP surface is 29 tools (see packages/mcp/src/server.ts);
the 6 listed above are the high-frequency exploration tools. For the
full inventory, use the /codehub-guide skill.
AMBIGUOUS_REPO
When two or more repos are indexed on this machine, per-repo tools require
an explicit repo: (or the repo_uri: alias — a Sourcegraph-style URI
such as github.com/org/repo, or local:<hash> for unpublished repos)
and return AMBIGUOUS_REPO otherwise. The error envelope carries a
structured _meta payload on structuredContent.error:
{ error_code: "AMBIGUOUS_REPO", jsonrpc_code: -32602, choices: [ { repo_uri, default_branch, group } ] (capped at 10), total_matches, hint } —
so the calling agent can retry deterministically with a single repo_uri
from choices. When total_matches > choices.length, the caller knows
the list was truncated.
See ADR 0012 (docs/adr/0012-repo-as-first-class-node.md) for the
rationale behind repo_uri as a first-class node attribute. The
repo_uri shape was promoted to a typed graph attribute by AC-M6-1
(packages/core-types/src/nodes.ts:524-552). group_cross_repo_links
(the AC-M6-3-reframed MCP tool) and the group_* family (AC-M6-4) all
emit repo_uri in the same canonical form, so a caller can use any of
those tools' repo_uri outputs as input to AMBIGUOUS_REPO.choices
retries.
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.
- yesterday First seen · 132 lines · 1,722 tokens per session scan A 18bc3bd857ef
opencodehub CLAUDE.md is an instructions file published in the GitHub repository theagenticguy/opencodehub (3 stars, last pushed 20d ago), licensed Apache-2.0. It adds 1,722 tokens to every session, about $0.0086 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
n8n-skills CLAUDE.md
Instructions for czlonkowski/n8n-skills, covering claude.md, project overview, repository structure, the 14 skills and 1. n8n expression syntax.
Tutorial_AwesomeModernCPP AGENTS.md
Instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
python-cheatsheet copilot-instructions.md
Copilot instructions for labex-labs/python-cheatsheet, covering python cheatsheet - ai coding assistant instructions, project overview, architecture & key patterns, content structure and routing & layout system.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.