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 skills add AlanHuang168/AI-Project-Workflow --skill retrogit clone --depth 1 https://github.com/AlanHuang168/AI-Project-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/alanhuang168/ai-project-workflow/retro)<a href="https://agentmods.dev/skills/alanhuang168/ai-project-workflow/retro"><img src="https://agentmods.dev/badge/skills/alanhuang168/ai-project-workflow/retro/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/alanhuang168/ai-project-workflow/retro"><img src="https://agentmods.dev/badge/skills/alanhuang168/ai-project-workflow/retro.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 | $0.00000 | $0.00592 |
| Opus 5 | $0.00000 | $0.00296 |
| Sonnet 5 | $0.00000 | $0.00118 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
retro 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 9d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: retro description: Summarize outcomes, deviations, root causes, reusable assets, and improvement actions. Use when the project is complete, when delivery needs a retrospective, or when the user invokes /retro. version: 1.0.0 stage: retro
Goal
Review the full workflow and capture outcomes, deviations, root causes, reusable assets, and improvements for the next iteration.
Use Cases
- The user invokes
/retro. - The user asks for a project retrospective.
- The project needs a delivery summary.
Preconditions
deployis complete, or the user explicitly approves skipping deployment and records the reason.- Upstream documents and code are readable.
Required Context
AGENTS.md.ai-workflow/state.jsoncore/templates/RETRO.template.mddocs/PRD.mddocs/ARCH.mddocs/SDD.mddocs/TEST.mddocs/REVIEW.mddocs/DEPLOY.md, if present- Relevant source and test files
Inputs
- Full project context.
- User feedback about results, quality, time, and risk.
Allowed Changes
docs/RETRO.md.ai-workflow/state.json- Optional candidate improvements for team rules, but only after user confirmation.
Steps
- Read workflow state, upstream documents, review report, deployment guide, and code.
- Summarize completed and incomplete work.
- Compare plan versus actual outcome and analyze root causes.
- Record what went well, problems, improvement actions, and reusable assets.
- Identify next-version recommendations and priorities.
- Write
docs/RETRO.md. - Update workflow state:
documents.retro = "complete", addretrotocompletedStages, setcurrentStage = "retro", and update the timestamp.
Outputs
docs/RETRO.md- Updated
.ai-workflow/state.json
Acceptance Criteria
- RETRO includes outcome, plan versus actual, what went well, problems and root causes, improvement actions, and reusable assets.
- Incomplete work and deviations are recorded honestly.
- The retrospective is not only praise or a chronological log.
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.
- 9d ago First seen · 84 lines · 0 tokens per session scan A d6135fc79218
retro is a skill published in the GitHub repository AlanHuang168/AI-Project-Workflow (28 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 592 tokens. 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 2026-08-30.
Other skills, from other repositories
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.
handoff-protocols
Manages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs to hand off, hand over, or transition a project; pass work to another person or…
workflows
Clay workflows — build and edit automations with clay workflows nodes/graph/actions/code/triggers (CLI). Use when building or editing Clay workflows.
workflows-optimize-credits
Clay workflows — reduce a workflow's credit and LLM cost via the CLI (clay workflows commands). Identifies expensive patterns and suggests cheaper alternatives.
workflows-vs-tables
Clay Workflows vs Tables — conceptual explainer for a customer asking what the difference is or which one to use. Read this when explaining the two products or recommending one for a use case. Users cannot build tables via the CLI/API; if a task needs a new table, surface that to the user & explain workflows are the…
workflows-simplify
Clay workflows — simplify a workflow via the CLI (clay workflows commands): merge redundant nodes, cut unnecessary complexity, and replace LLM nodes with deterministic alternatives where possible.