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 cunhaax/ai-workflow --skill workflow-retrogit clone --depth 1 https://github.com/cunhaax/ai-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/cunhaax/ai-workflow/workflow-retro)<a href="https://agentmods.dev/skills/cunhaax/ai-workflow/workflow-retro"><img src="https://agentmods.dev/badge/skills/cunhaax/ai-workflow/workflow-retro.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.01978 |
| Opus 5 | $0.00048 | $0.00989 |
| Sonnet 5 | $0.00019 | $0.00396 |
| Haiku 4.5 | $0.00010 | $0.00198 |
Grade A, and why
workflow-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 7d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/workflow-retro — Record the Feature's Workflow Outcome
Run this skill at the end of a feature session — typically after the PR is
opened (Step 9 of /feature), or when the feature is abandoned. It records
what the workflow actually did for this feature: which steps ran, what each
one caught, and what that changed. Over several features, these records are
the evidence base for tuning the workflow — which steps earn their cost,
which are candidates for skip rules.
This is the outcome half of the record. The cost half (tokens per
step, wall-clock, file-read overlap) is computed from the session transcripts
by the companion /workflow-inspect skill and appended to the same file
later. If that skill is not installed yet, the Cost section simply stays
pending — nothing here depends on it.
Ground rules:
- Facts come from artifacts. Fill each field from the PR body,
git log, and the plan/critique/review/QA outputs in this session — not from memory alone when an artifact exists. Anything not established is recorded asunknown, never guessed. - The log is local evaluation data.
.workflow-log/is gitignored — never commit it or its contents, and never move it into the repo history. - One file per feature branch. If a file for the current branch already exists (a previous retro, or the feature spans multiple sessions), update it — fill gaps, correct facts, append the new session ID — instead of creating a duplicate. Exception: if the existing file evidently records a different feature that reused the branch name (its PR is already merged, or its dates are far from this session's), ask the user whether to replace it or pick another filename — do not merge two features into one record.
- Writing the log file (and creating its directory) is the only mutation this skill performs.
- The skill assumes a
/featuresession. In a session that ran only part of the workflow (an ad-hoc/plan-draft, a review-only pass), record what applies and mark the restn/a.
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.
- 7d ago First seen · 167 lines · 97 tokens per session scan A 6e6b03924294
workflow-retro is a skill published in the GitHub repository cunhaax/ai-workflow (5 stars, last pushed 11d ago), licensed MIT. It adds 97 tokens to every session and 1,978 once invoked, about $0.0005 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 skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
email-systems
Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.