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.
git clone --depth 1 https://github.com/skullninja/coco-workflowWrote 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/commands/skullninja/coco-workflow/sync)<a href="https://agentmods.dev/commands/skullninja/coco-workflow/sync"><img src="https://agentmods.dev/badge/commands/skullninja/coco-workflow/sync/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/commands/skullninja/coco-workflow/sync"><img src="https://agentmods.dev/badge/commands/skullninja/coco-workflow/sync.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 | $0.00020 | $0.00764 |
| Opus 5.5 | $0.00008 | $0.00306 |
| Sonnet 5.5 | $0.00004 | $0.00153 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
sync 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
$ARGUMENTS can optionally specify:
--dry-run-- show what would change without making updates--epic {name}-- sync a specific epic (default: active)
Setup
- Read
.coco/config.yamlforissue_trackerconfiguration. - If
issue_tracker.provideris "none", report "No issue tracker configured" and exit.
Execution
0. Clean Up Stale Worktrees
Remove stale git worktree references left by crashed or completed agents:
git worktree prune
If .claude/worktrees/ contains directories with no corresponding git worktree, remove them:
git worktree list --porcelain
Compare against directories in .claude/worktrees/. Remove any orphaned directories.
1. Load Tracker State
coco-tracker list --json --epic {epic-id}
Parse all tasks with their statuses and issue_key metadata.
2. Load Issue Tracker State
For each tracker task that has an issue_key:
If "linear":
Use: mcp__plugin_linear_linear__get_issue
Parameters:
id: {issue_key}
If "github":
If github.use_projects is true:
- Read
.coco/state/gh-projects.jsonand find the feature entry whereproject_numbermatches the task'sgh_project_numbermetadata. Extractproject_id,status_field_id, andstatus_optionsfrom that entry. - Query project board status as source of truth:
Match each task'sgh project item-list {project_number} --owner {github.owner} --format jsongh_project_item_idto get its current board column status. - Backfill detection: For tasks with
issue_keybut nogh_project_item_id(pre-existing issues created before Projects V2 was enabled), offer to backfill:
Then update tracker metadata with the newgh project item-add {project_number} --owner {github.owner} --url {issue_url}gh_project_item_id.
If github.use_projects is false (legacy):
gh issue view {issue_number} --json state,labels
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 First seen · 112 lines · 20 tokens per session scan A 6295cd89d29a
sync is a command published in the GitHub repository skullninja/coco-workflow (8 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 764 once invoked, about $0.0001 per session on Opus 5.5. 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
ccc
CC Commander Hub — interactive menu derived from adventure JSON files. 450+ skills, 11 CCC domains, 80+ commands, 9 modes.
ccc-spawn
Plan and launch parallel Claude Code peers (quick, team, swarm or domain expert), each on its own branch and worktree with non-overlapping files, then track or stop them. Use when work splits into independent parts that should run in separate sessions.
ccc-improve
Run the continuous-improvement pipeline: scan GitHub and npm for new Claude Code tooling, score proposals, and approve or reject them in a local queue. Use when reviewing ecosystem findings or deciding what to adopt next.
ccc-linear
Show the Linear project board by status with a progress bar, pick an issue to start work on, or create a new issue, with every Linear write confirmed first. Use when you want to see or act on your Linear project from the session or the ccc CLI.
ccc-makeover
Score project health with X-Ray, apply the top recommendations in impact order with your OK for each, and show the before and after score. Use when you want the highest-impact project health fixes applied and measured.
ccc-office-hours
Stress-test a product idea before writing code through product, technical and user lenses, ending in BUILD IT, SIMPLIFY FIRST, RESEARCH MORE or KILL IT. Use when deciding whether a feature or product is worth building.