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/gtrabanco/agentic-workflow/generate-docsnpx skills add gtrabanco/agentic-workflow --skill generate-docsgit clone --depth 1 https://github.com/gtrabanco/agentic-workflowWhat 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 | $0.00049 | $0.01508 |
| Opus 5 | $0.00024 | $0.00754 |
| Sonnet 5 | $0.00010 | $0.00302 |
| Haiku 4.5 | $0.00005 | $0.00151 |
Grade A, and why
generate-docs 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Docs
Turn the knowledge produced by a unit of work into developer documentation a contributor can read on the project's docs website — incrementally, as a by-product of shipping, so a public repo's docs stay current instead of rotting. A commit says what changed; a guide says how to use it ("how do I create a domain event and where do I register its handler").
Turn contract — verify before ending the turn
✓ The docs adapter was resolved through the Step 0 detection checklist and the
outcome (adapter name, or NOT CONFIGURED) is stated in the report
✓ Every generated/updated page is WRITTEN to disk (paths listed in the report)
and carries the provenance frontmatter — or zero pages were written and the
report says exactly why
✓ The verify step was RUN (docs build command or link check) and its result
pasted — never assumed
✓ Artifact language: explicit user instruction > the project's declared docs
language > English. The CONVERSATION language never decides
✓ The fixed report block is printed, then the closing `→ Next:` block, as the
ABSOLUTE last output
About to end the turn with any box unchecked? The turn is NOT done — complete the missing box first (weak models drop end-of-document duties; this list is first on purpose).
When to use
- After finishing a unit of work —
execute-phaserecommends this skill at close-out when the project declares a docs site: document what the unit changed while the context is fresh. - On demand for a specific area:
generate-docs src/domain/events/. --review— export the latestreview-changereport as a docs page so humans can review findings from the website.- Not for writing SPECs/planning docs (
plan-feature), session journals (log-session), or reviewing code (review-changeproduces the findings; this skill only publishes an existing report on request).
Progressive loading — resolve the docs route
The reference allowlist is exactly the three paths below. Read them in this order; every selected resource is normative and one hop from this entrypoint.
What ships with it
3 files 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.
- 2d ago First seen · 146 lines · 49 tokens per session scan A f93afe9167cc
generate-docs is a skill published in the GitHub repository gtrabanco/agentic-workflow (20 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 1,508 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 2026-08-30.
Other skills, from other repositories
think-like-me
Personal engineering rules and reasoning patterns the user has curated over time. Consult BEFORE writing, modifying, debugging, or designing any technical feature — rules often cover domain-specific gotchas (e.g., mobile audio timers need background mode) that generic answers miss. Also triggers on /learn-this, "learn…
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.