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/5uck1ess/devkit/autoloopnpx skills add 5uck1ess/devkit --skill autoloopgit clone --depth 1 https://github.com/5uck1ess/devkitWhat 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 | $0.00041 | $0.00688 |
| Opus 5 | $0.00020 | $0.00344 |
| Sonnet 5 | $0.00008 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
autoloop 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoloop
Autonomous codebase improvement inspired by karpathy/autoresearch. Audit the codebase, pick the highest-impact change, fix it, measure the result, keep or revert, repeat.
Before Starting
Use AskUserQuestion to gather these inputs. Do NOT proceed without answers.
1. Objective
Ask: "What do you want to improve? (e.g., test coverage, lint errors, performance, security)"
2. Metric Command
Ask: "What command measures success? (e.g., go test -cover ./..., npx jest --coverage, ruff check . | wc -l)"
If the user doesn't have one, detect the stack and suggest:
| Stack | Default metric | Direction |
|---|---|---|
| Go | go test -cover ./... |
higher-is-better (coverage %) |
| TypeScript | npx jest --coverage |
higher-is-better (coverage %) |
| Python | pytest --cov |
higher-is-better (coverage %) |
| Rust | cargo test |
higher-is-better (pass count) |
| Go (lint) | go vet ./... 2>&1 | wc -l |
lower-is-better (error count) |
| Any (lint) | <linter> . 2>&1 | wc -l |
lower-is-better (error count) |
Confirm with the user: "I'll use <command> with . Correct?"
3. Direction
If not obvious from the metric, ask: "Is higher or lower better for this metric?"
4. Iterations
Ask: "How many improvement cycles? (default: 10, max recommended: 50)"
5. Scope (optional)
Ask: "Any scope constraints? (e.g., only src/engine/, only .py files, or everything)"
If the user says "everything" or skips, leave scope open.
Invoke the Workflow
Start the workflow via the devkit engine:
Assemble the input as a single string: "<objective> | metric: <command> | direction: <higher/lower>-is-better | iterations: <N> | scope: <constraint or 'all'>".
Use the devkit_start tool with workflow: "autoloop" and input: "{input}".
Then follow each step the engine returns. Call devkit_advance after completing each step. The engine controls step order, gates, and loops. Do NOT skip steps.
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 · 67 lines · 41 tokens per session scan A 522b03143061
autoloop is a skill published in the GitHub repository 5uck1ess/devkit (5 stars, last pushed 13d ago), licensed MIT. It adds 41 tokens to every session and 688 once invoked, about $0.0002 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
dynamic-workflows
Ultracode / Max-Parallel mode — dynamic workflows fan work out across tens–hundreds of adversarially-verified parallel subagents for large, decomposable jobs (codebase-wide audits, big migrations, cross-checked research). Opt-in; higher token spend.
cost-efficiency
Smart Routing — the DEFAULT CCGodMode routing policy. Risk-based, minimal-agent paths that preserve required safety gates for the changed scope.
agent-teams
Experimental Agent Teams orchestration — run CCGodMode agents as parallel teammates with SharedTaskList coordination (requires CLAUDECODEEXPERIMENTALAGENTTEAMS=1).
quality-gates
Parallel quality gate orchestration — @validator and @tester run simultaneously after @builder, with mandatory decision matrix for pass/fail routing.
sprint-planning
Plan-first orchestration (ADR-004): comprehensive PLAN.md, sprint files with write-scope ownership, preflight checks, serialized integration, and the release sprint. Use for any non-trivial or multi-part request BEFORE dispatching agents.
workflows
CCGodMode Full-Gates workflow definitions — used for high-risk work and when Smart Routing escalates. Default routing is Smart Routing (skills/cost-efficiency/).