Borrowing it
Nothing to install: this file belongs to skwashd/ccodolo. 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/skwashd/ccodolo/main/AGENTS.mdgit clone --depth 1 https://github.com/skwashd/ccodoloWrote 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/skwashd/ccodolo/agents-md)<a href="https://agentmods.dev/instructions/skwashd/ccodolo/agents-md"><img src="https://agentmods.dev/badge/instructions/skwashd/ccodolo/agents-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/skwashd/ccodolo/agents-md"><img src="https://agentmods.dev/badge/instructions/skwashd/ccodolo/agents-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 | $0.03364 | $0.03364 |
| Opus 5.5 | $0.01346 | $0.01346 |
| Sonnet 5.5 | $0.00673 | $0.00673 |
| Haiku 4.5 | $0.00336 | $0.00336 |
Grade A, and why
ccodolo 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 1mo 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.
This is a copy
100% identical to skills AGENTS.md — 222 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Guide for AI Coding Assistants
This document provides development guidelines for AI-powered coding tools working on the CCoDoLo project itself.
For project features, usage, and architecture: See README.md
Note: AGENTS.md is a symlink to this file so non-Claude assistants discover it too — edit CLAUDE.md, not the symlink.
What This Project Is
CCoDoLo is a meta-project - it provides sandboxed Docker containers for running AI coding assistants (including you). When modifying this codebase, you're improving the infrastructure that runs AI agents safely.
Repository Structure
ccodolo/
├── .github/
│ ├── dependabot.yml # Weekly updates for github-actions and gomod
│ ├── zizmor.yml # zizmor security scanner config
│ └── workflows/
│ ├── release.yml # goreleaser (triggered by v* tags)
│ ├── updates.yml # daily agent + tool version bumps (opens PRs)
│ ├── validate.yml # go vet, go test, golangci-lint, cross-platform build, docker image smoke test
│ └── zizmor.yml # GitHub Actions security scanning
├── .golangci.yml # Default linters + gofmt as a formatter check
├── .goreleaser.yml # Cross-platform binaries + checksums + build attestation
├── go.mod / go.sum
├── main.go # Entrypoint → cmd.Execute()
├── cmd/
│ ├── root.go # cobra root command, flags, main run() logic, TUI
│ ├── repair.go # repair-worktrees subcommand (host-side git worktree repair)
│ └── version.go # version subcommand
├── internal/
│ ├── agent/
│ │ ├── agent.go # Agent enum, metadata registry
│ │ └── agent_test.go
│ ├── config/
│ │ ├── config.go # TOML struct, Load/Save, merge, validate
│ │ ├── config_test.go
│ │ ├── migrate.go # ccodolo.config → ccodolo.toml migration
│ │ └── migrate_test.go
│ ├── docker/
│ │ ├── build.go # Image build orchestration, build-context staging
│ │ ├── build_test.go
│ │ ├── dockerfile.go # Dockerfile template rendering
│ │ ├── dockerfile_test.go
│ │ ├── exec_unix.go # execCLI: replace the process via execve (see Architecture Notes)
│ │ ├── exec_windows.go # execCLI: child process with inherited console (no execve on Windows)
│ │ ├── hash.go # SHA-256 image tag computation
│ │ ├── hash_test.go
│ │ ├── hooks.go # Host-side startup-hook pre-flight warning
│ │ ├── hooks_test.go
│ │ ├── run.go # docker run / docker exec argv (--mount binds, env, TERM defaults)
│ │ ├── run_test.go
│ │ ├── runtime.go # Runtime enum (docker/apple), host checks
│ │ └── runtime_test.go
│ ├── fsutil/
│ │ ├── copy.go # CopyDir/CopyFile, mode-preserving
│ │ └── copy_test.go
│ ├── project/
│ │ ├── project.go # Dir creation, template copying
│ │ ├── project_test.go
│ │ ├── setup.go # Agent-specific JSON config (copilot/kiro)
│ │ └── setup_test.go
│ ├── tool/
│ │ ├── custom_tools_test.go
│ │ ├── readme_test.go # Fails when the README Dev Tools table drifts from the catalog
│ │ ├── tool.go # Tool catalog, dependency resolution
│ │ └── tool_test.go
│ └── updater/ # Automated tool-version bumper (not in released binary)
│ ├── main.go # Flags: -check, -json, -write, -only, -timeout, -allow-unverified
│ ├── version.go # Numeric-tuple version parse/compare
│ ├── plan.go # Candidate selection, bump classification
│ ├── source.go # Fetcher interface + registry dispatch
│ ├── fetch_docker.go # Docker Hub API
│ ├── fetch_github.go # GitHub Releases API
│ ├── fetch_npm.go # npm registry API
│ ├── fetch_pypi.go # PyPI JSON API
│ ├── fetch_quay.go # quay.io API
│ ├── rewrite.go # Anchored-regex file rewriters
│ ├── git.go # exec-based git helpers
│ ├── version_test.go
│ └── rewrite_test.go
├── embedded/
│ ├── embed.go # go:embed directives
│ ├── Dockerfile.tmpl # Templatized Dockerfile
│ ├── dotfiles/ # Shell configurations (.bashrc, .zshrc.local, .inputrc)
│ └── scripts/ # Container startup scripts (git worktree hygiene)
├── docs/
│ └── custom-tools.md # Custom tool catalog reference (custom-tools.json)
└── template.example/ # Example project templates
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.
- 1mo ago Changed · +220 lines · +3,360 tokens per session e49b8cb069ac
- 2mo ago First seen · 1 lines · 4 tokens per session scan A 6ebdb617a810
ccodolo AGENTS.md is an instructions file published in the GitHub repository skwashd/ccodolo (24 stars, last pushed yesterday), licensed MIT. It adds 3,364 tokens to every session, about $0.0135 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to skills AGENTS.md, differing in 222 lines, and is treated as a copy.
ccodolo AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ccodolo AGENTS.mdskwashd/ccodolo | Instructions file | 24 | yesterday | MIT | A | 3,364 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |