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/rube-de/cc-skills/dev-taskgit clone --depth 1 https://github.com/rube-de/cc-skillsWhat 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 | $0.00043 | $0.00477 |
| Opus 5 | $0.00022 | $0.00238 |
| Sonnet 5 | $0.00009 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
dev-task 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 2d 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.
What it actually says
ROLE: Coordinator only. You do NOT edit source code, test files, or project docs. You delegate all implementation, testing, review, plan writing, and doc updates to teammates. You verify plan/report artifacts written by teammates.
Narrow exception: One-shot Bash file-appends for plugin-install side effects (specifically the discovery-hint install performed in dev-workflow.md §9 step 6) are explicitly permitted. This exception does NOT extend to Edit/Write/NotebookEdit on any file, nor to broader Bash file edits on source, test, or doc content.
/dev-task — Development Phase
Target: $ARGUMENTS (pass the plan file path, e.g. .dev/cdt/plans/plan-20260207-1430.md)
You are the Lead for the development phase. Create an agent team where developer teammate, code-tester teammate, qa-tester teammate, and reviewer teammate collaborate with direct peer messaging for iteration loops.
Team
| Role | How | When | Why |
|---|---|---|---|
| Developer teammate | Teammate | Always | Iterates with code-tester teammate on failures, reviewer teammate on issues |
| Code-tester teammate | Teammate | Always | Messages developer teammate directly with unit/integration test failure details |
| QA-tester teammate | Teammate | Always | UX testing (Storybook + agent-browser) for UI tasks; integration/smoke testing for non-UI tasks |
| Reviewer teammate | Teammate | Always | Messages developer teammate directly with fix requests |
| Researcher subagent | Subagent (researcher) |
Always | On-demand doc lookups, Lead relays |
Follow the development workflow defined in @dev-workflow.md.
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.
- 2d ago First seen · 27 lines · 43 tokens per session scan A 14f6f94f3b98
dev-task is a command published in the GitHub repository rube-de/cc-skills (10 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 477 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 commands, from other repositories
xstatus
Executed by Main Agent directly. Scan the project, collect workflow state, and generate an HTML status report.
org-reorg-trauma-audit
Pre-reorg trauma audit and sequencing plan. Opens with the 70%+ reorg-failure honesty, runs trauma history + threat-activation forecast (SCARF), produces a wave-based sequencing plan, communication architecture grounded in Kotter + Bridges, per-team mitigation, and post-reorg Talent IS monitoring cadence. Refuses…
init
First-run teamctl onboarding — from no-teamctl-installed to a running supervised team in one conversation.
org-span
Span-of-control architecture audit and redesign. Audits per-manager spans against research bounds (5-9 for complex knowledge work; up to 15-20 for repetitive supervised). Surfaces pattern flags (top-heavy / middle-thin / over-spanned individual contributors), redesign recommendations with sequencing, and a transition…
dashboard
Phase 3 monitoring — System health, execution insights, and velocity analytics.
run
Execute an approved PRD using feature branch workflow (v7.0). This command generates briefs, auto-reviews them, allows user iteration, and then orchestrates execution.