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 skills/codoop/codoop-flow/codoop-executenpx skills add Codoop/codoop-flow --skill codoop-executegit clone --depth 1 https://github.com/Codoop/codoop-flowWhat 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 | $0.00082 | $0.03786 |
| Opus 5 | $0.00041 | $0.01893 |
| Sonnet 5 | $0.00016 | $0.00757 |
| Haiku 4.5 | $0.00008 | $0.00379 |
Grade A, and why
codoop-execute 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codoop-execute orchestration
You are the orchestrator of the codoop-flow Agent-Centric loop (Loop 3, engineering
design §5). You do the intelligent work in this session: writing code,
self-healing, review judgment, and living-doc sync. A small guardrail CLI
(runtime/codoop-flow/codoop_tools.py) handles everything that must be
100% deterministic — claiming tickets, moving folders, managing the isolated git
worktree, checking the UI screenshot gate, committing.
Never do the CLI's job by hand (don't move ticket folders or create worktrees
yourself) — always call the tool, because those steps must never be guessed.
Plugin Runtime
Codex, Claude Code, and Cursor install the whole plugin. All skills call the same Runtime:
$SKILL/../../runtime/codoop-flow/
├── codoop_tools.py guardrail CLI (Loop 3)
├── codoop.py setup CLI
├── codoop-ticket.py ticket lifecycle CLI
├── codoop_lib_v1/ shared Python modules
└── agents/ shared review personas
First, locate $SKILL — the absolute path of the directory containing this
SKILL.md. Build every path below from it and invoke the Runtime by absolute path.
Prerequisites
- A
codoop_flow.tomlpointing at the target repo. All CLI calls take--config <path>. Ask the user for the path if it isn't obvious; reuse it for every call in the run.
Read output_language from that config before starting. Use it for all
user-facing replies and generated prose, including reports and delegated agent
prompts. "auto" or a missing field follows the user's current language. An
explicit request for the current task overrides the config. Do not translate
source-code identifiers, commands, logs, or required protocol literals.
Read user_role from that config; a missing value means general. It changes
only the live conversation: use normal professional terms inside the user's
field, and explain cross-field topics in plain language. The user's current
request for simpler or more professional language overrides it. Do not apply
this profile to code, ticket documents, reports, or delegated agent prompts;
those remain precise and professional.
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 · 293 lines · 82 tokens per session scan A 7c549c3248de
codoop-execute is a skill published in the GitHub repository Codoop/codoop-flow (5 stars, last pushed 8d ago), licensed MIT. It adds 82 tokens to every session and 3,786 once invoked, about $0.0004 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 skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
chatbot
Use when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human handoff, launch metrics and kill switch. NOT the agent loop or RAG index under it (that is building-agents), NOT a human answering one ticket…
agent-safety
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or…
antidote
Stop AI agents from patching symptoms. Use this skill when coding, reviewing, refactoring, auditing, committing fixes, or adding guards, validation, workarounds, or 20+ lines without deleting code.
anti-slop-design
Category-aware design skill that builds distinctive, production-grade UIs. Brand-vs-product register, color strategy commitment, scene-based theme choice, palettes, font pairings, UX patterns, shadcn/token integration, empty-error-loading copy, secondary slop signals, multimodal design parity from mocks, and a…
3d-web-experiences
Build distinctive, performant, production-grade 3D on the web with Three.js, React Three Fiber, and WebGL. Use when the user asks to "build a 3D scene", "add a 3D hero/landing", "make a product viewer/configurator", mentions three.js / react-three-fiber / r3f / drei / webgl / shaders, or asks to make an existing 3D…