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 skills/cunhaax/ai-workflow/workflow-inspectnpx skills add cunhaax/ai-workflow --skill workflow-inspectgit 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-inspect)<a href="https://agentmods.dev/skills/cunhaax/ai-workflow/workflow-inspect"><img src="https://agentmods.dev/badge/skills/cunhaax/ai-workflow/workflow-inspect.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 | $0.00089 | $0.00977 |
| Opus 5 | $0.00044 | $0.00489 |
| Sonnet 5 | $0.00018 | $0.00195 |
| Haiku 4.5 | $0.00009 | $0.00098 |
Grade A, and why
workflow-inspect 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 6d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/workflow-inspect — Compute the Feature's Workflow Cost
Run this skill after /workflow-retro has recorded a feature's outcome, and
within the transcript retention window. It fills the record's pending
## Cost section with numbers computed from the raw session transcripts:
tokens and wall-clock per sub-agent, the sub-agents' share of the total,
and the handoff tax (files the planner read that the main agent re-read).
Together the two halves say what each workflow step cost and caught —
the evidence base for tuning the workflow (see Evolving the System in
the AI Workflow plugin's own documentation).
Ground rules:
- Numbers come from the script, verbatim. Never estimate, adjust, or
fill in a figure the script did not print. If the script fails or its
output carries warnings, surface them to the user as-is (Rule 2 in
AGENTS.mdapplies to the script like any other command). - The only mutation is the log file. Replacing the
## Costsection of the chosen record(s) — after the user confirms — is the only write this skill performs. Never commit anything;.workflow-log/stays local. - The bundled script (
inspect.py, in this skill's directory) is read-only: it parses transcripts and prints markdown to stdout.
Step 1 — Pick the record(s)
Resolve the log directory exactly as /workflow-retro does: .workflow-log/
under the main worktree (parent of
git rev-parse --path-format=absolute --git-common-dir). List the records
whose ## Cost section is still pending. One pending record → proceed with
it; several → ask which to inspect (offering "all" — each is one script run).
None → report that every record is already inspected and stop.
Step 2 — Gather the session IDs
Read the record's Sessions: line. If it is unknown, or Step 3 finds no
transcript for any listed ID, the cost is unrecoverable once transcripts are
pruned — with the user's confirmation, close the section honestly with
unavailable — transcripts pruned or session IDs unknown instead of leaving
pending forever.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 89 lines · 89 tokens per session scan A a37c6263ddf2
workflow-inspect is a skill published in the GitHub repository cunhaax/ai-workflow (5 stars, last pushed 9d ago), licensed MIT. It adds 89 tokens to every session and 977 once invoked, about $0.0004 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
golden-jupyter-dir
Use when testing the goldenjupyterdir golden build.
golden-man-kw
Use when testing the man golden build.
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.
golden-rss
Use when testing the rss golden build.
golden-chat-topics
Use when testing the goldenchattopics golden build.
golden-chat-single
Use when testing the goldenchatsingle golden build.