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/cluesmith/ci-channel/agents-mdgit clone --depth 1 https://github.com/cluesmith/ci-channelWhat 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 | $0.01697 | $0.01697 |
| Opus 5 | $0.00848 | $0.00848 |
| Sonnet 5 | $0.00339 | $0.00339 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
ci-channel 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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ci-channel CLAUDE.md — 91% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ci-channel - AI Agent Instructions
Note: This file follows the AGENTS.md standard for cross-tool compatibility with Cursor, GitHub Copilot, and other AI coding assistants. A Claude Code-specific version is maintained in
CLAUDE.md.
Project Overview
A Claude Code channel plugin that delivers real-time CI/CD notifications into running Claude Code sessions. Supports GitHub Actions, GitLab CI, and Gitea Actions. Built with the MCP (Model Context Protocol) SDK and published on npm as ci-channel.
This project uses Codev for AI-assisted development.
Architecture
See codev/resources/arch.md for the full architecture document.
Key components:
server.ts— MCP server entry point +setupsubcommand dispatchlib/forge.ts— Forge interface (strategy pattern for multi-forge support)lib/forges/github.ts— GitHub Actions forge (HMAC-SHA256,workflow_run,ghCLI)lib/forges/gitlab.ts— GitLab CI forge (token validation, Pipeline Hook,glabCLI)lib/forges/gitea.ts— Gitea Actions forge (HMAC-SHA256,workflow_run, fetch API)lib/config.ts— Configuration loading (CLI args + env vars +.envfile)lib/bootstrap.ts— First-run auto-provisioning (secret generation, smee channel, setup notification)lib/handler.ts— Webhook handler pipeline (validate → dedup → filter → notify)lib/webhook.ts— Signature validation, event parsing, deduplicationlib/notify.ts— Notification formatting and sanitizationlib/reconcile.ts— Startup reconciliation and job enrichmentlib/project-root.ts— Walk-up project root detection (.mcp.json/.git)lib/state.ts— Plugin state persistence (state.jsonread/write)lib/setup.ts—ci-channel setupinstaller — supports all three forges and Codev auto-integration (Spec 5 + Spec 7, ≤300 lines, single file, no DI)
Configuration
State is project-scoped as of v0.2.0. Each project gets its own <project-root>/.claude/channels/ci/state.json and <project-root>/.claude/channels/ci/.env. Project root is detected via findProjectRoot() (walks up for .mcp.json or .git/).
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 · 119 lines · 1,697 tokens per session scan A 214121056087
ci-channel AGENTS.md is an instructions file published in the GitHub repository cluesmith/ci-channel (4 stars, last pushed 4mo ago), licensed MIT. It adds 1,697 tokens to every session, about $0.0085 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
kubevirt-tekton-tasks AGENTS.md
Instructions for kubevirt/kubevirt-tekton-tasks, covering kubevirt tekton tasks - project guide, jira task management, documentation, project structure and key relationships.
foundry-local cpp-ci-test-policy.instructions.md
Use when adding a new test fixture, modality, or model dependency to the C++ integration test suite, or when debugging unexpected GTESTSKIP messages in CI.
docker-zoneminder CLAUDE.md
Instructions for jantman/docker-zoneminder, covering claude.md, project overview, build and test, ci/cd and architecture.
Powershell-Copilot-Standards cicd.instructions.md
Sets up comprehensive CI/CD pipelines for PowerShell projects with automated testing and deployment.
local-ci CLAUDE.md
Claude Code instructions for redwoodjs/local-ci, covering local ci — agent instructions, rules, ci and code.
pipelines CLAUDE.md
Instructions for rios0rios0/pipelines, covering claude.md, what this is, commands, architecture and 5-stage pipeline model.