Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kryptobaseddev/cleonpx agentmods add skills/kryptobaseddev/cleo/ct-dev-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/skills/kryptobaseddev/cleo/ct-dev-workflow)<a href="https://agentmods.dev/skills/kryptobaseddev/cleo/ct-dev-workflow"><img src="https://agentmods.dev/badge/skills/kryptobaseddev/cleo/ct-dev-workflow/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/skills/kryptobaseddev/cleo/ct-dev-workflow"><img src="https://agentmods.dev/badge/skills/kryptobaseddev/cleo/ct-dev-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 90 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Tool Misuse · line 217 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00076 | $0.04682 |
| Opus 5.5 | $0.00030 | $0.01873 |
| Sonnet 5.5 | $0.00015 | $0.00936 |
| Haiku 4.5 | $0.00008 | $0.00468 |
Grade A, and why
ct-dev-workflow 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 3d 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 — 563 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow Context Injection
Opt-in unified-hook releases use the numbered vYYYY.MM.N-canary.N channel
through the normal release plan/open and OIDC workflow. The release-preparation
workflow accepts this channel explicitly; publication stays on canary and does
not advance to latest. Preserve registry retries and installed-package soak
checks. Stable promotion needs the separately retained, source-bound live harness
and hosted VidaPeps pilot evidence; missing or unavailable verification holds it.
The stable target may follow the canary base when npm has already advanced, but
every receipt must still bind to the exact canary and implementation digest.
Reject backward targets and prerelease targets; use the normal stable pipeline.
Before editing, inspect focus/briefing authority and coverage. Missing evidence means UNKNOWN impact; current static coverage does not prove every runtime caller. Task start, verification, completion, and handoff expose assessed coverage. Preserve these limitations in PR and handoff claims, and recheck after source changes. Use the repair matrix and sourced foreground resolutions; verify postconditions and retain receipt recovery. Record actionable learning rather than empty traces.
Protocol: @src/protocols/contribution.md Type: Context Injection (cleo-subagent) Version: 3.0.0
Purpose
Context injection for development workflow tasks spawned via cleo-subagent. Provides domain expertise for atomic commits with task traceability, conventional commit messages, and systematic release processes.
Core Principle: Task-Driven Development
CRITICAL: NO code changes or commits without a tracked task.
Every commit MUST be traceable to a CLEO task. This ensures:
- Work is planned and tracked
- Changes are reviewable and reversible
- Progress is measurable
- Context is preserved for future agents
Immutable Constraints (WORKFLOW)
| ID | Rule | Enforcement |
|---|---|---|
| WF-001 | Task required | NO commits without CLEO task reference |
| WF-002 | Branch discipline | NO commits to main/master |
| WF-003 | Atomic commits | ONE logical change per commit |
| WF-004 | Conventional format | <type>(<scope>): <description> |
| WF-005 | Tests before push | Relevant tests MUST pass |
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.
- 3d ago Changed · +10 lines e7e7e4b495cf
- 4d ago Changed · +12 lines 676b483573e0
- 5d ago Changed · +6 lines 79c30200ab19
- 8d ago Changed · +7 lines ed989bd8b9c0
- 9d ago Changed · +40 lines ade57f31a7b5
- 10d ago Changed · +29 lines f439944e586e
- 16d ago Changed · +5 lines 6b067a394ca8
- 20d ago Changed · +4 lines 07cd8e17b431
- 21d ago Changed · +14 lines 59b41340e455
- 22d ago First seen · 436 lines · 76 tokens per session scan A ce335b5b50f1
ct-dev-workflow is a skill published in the GitHub repository kryptobaseddev/cleo (159 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 4,682 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
smith-build
Autonomous build phase — generates tasks, implements, tests, commits, pushes, merges, and produces release notes. Runs without user interaction.
git-ship
An automated Git release workflow that takes code changes through a branch, commit, pull request, review checks, squash merge, and return to the main branch. A pull request is a request to review and merge changes into a shared branch.
auto-build-loop
Autonomous build driver after SDD spec approval: phase-scoped headless build sessions, driver-owned commits, cross-provider review gates, milestone pauses, and fail-closed escalation — under explicit opt-in autonomy profiles.
git-workflow
Branching strategies, conventional commits, PR templates, and merge vs rebase guidance. Activate when starting features, creating PRs, or managing releases.
github-delivery
Owns Git/GitHub delivery from scoped repository work through pull requests, reviews and CI handling, backports, release preparation, merge, and closure. Use for GitHub pull request or PR delivery, PR security reviews, branch or commit operations, release preparation, stacked or backport PRs, ongoing PR and CI watch or…