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 commands/skullninja/coco-workflow/loopgit clone --depth 1 https://github.com/skullninja/coco-workflowWhat 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 | $0.00028 | $0.03833 |
| Opus 5 | $0.00014 | $0.01917 |
| Sonnet 5 | $0.00006 | $0.00767 |
| Haiku 4.5 | $0.00003 | $0.00383 |
Grade A, and why
loop 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 — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
$ARGUMENTS is an epic ID or feature name. If empty, use the most recent open epic.
Setup
-
Read
.coco/config.yamlfor project configuration (includingprandloopsections). -
Determine the target epic from
$ARGUMENTSor most recent open epic. -
Read loop config. Defaults when a key is absent:
max_iterations: 20,no_progress_threshold: 3,pause_on_error: false,dashboard_every: 5,parallel.enabled: true,parallel.max_agents: 3,parallel.max_agent_attempts: 2.A project initialized before these defaults changed still carries the old values in its own
.coco/config.yaml, which is read in preference to any default here. Ifpause_on_erroristrueorparallel.enabledisfalsein this project, say so in the opening ledger line -- the user may not know their config predates the change, and/coco:setup migratereconciles it.
Pre-Loop Gate
Verify the epic is ready for autonomous execution:
coco-tracker epic-status {epic-id}
Check ALL before entering the loop:
- Tracker epic exists and has tasks
- Dependencies are set -- at least one task is unblocked (
readyreturns a result) - If issue tracker configured: every task has
issue_keyin metadata - If
pr.enabled: verify on afeature/*branch - If
pr.enabled: verify remote origin is configured (git remote -v) - If
pr.enabled: verifyghCLI is available
If any check fails, STOP and report what needs to be fixed.
Initialize Loop State
git branch --show-current
Record the output as the feature branch name for later use.
coco-tracker session-start "Autonomous loop for {epic-id}"
Set counters:
iteration = 0consecutive_no_progress = 0initial_commit_count = $(git rev-list --count HEAD)
Autonomous Loop
The Loop Does Not Stop To Report
This loop runs to completion inside one turn. Ending the turn is an exit, and the only legitimate exits are the ones enumerated under Exit Conditions below.
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 · 463 lines · 28 tokens per session scan A eb242b7ab444
loop is a command published in the GitHub repository skullninja/coco-workflow (7 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 3,833 once invoked, about $0.0001 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 commands, from other repositories
super-dev
Command "super-dev" from shangyankeji/super-dev, covering /super-dev (claude-code), 输入, super dev runtime contract, local knowledge contract and 首轮响应契约（首次触发必须执行）.
validate
You are the quality gate. Your job is to verify that a phase's implementation meets quality standards before the team moves to the next phase. No phase should advance until validation passes.
implement
You are the phase dispatcher. Your job is to route implementation work to the correct phase agent with the right context.
progress
You are generating a visual progress report showing which phases are complete, in-progress, or pending for the current feature.
commit
You are creating a conventional commit scoped to the current phase of work.
prd
You are generating a Product Requirements Document (PRD) for the project described below.