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/asteasolutions/ai-toolkit/docs-generatornpx skills add asteasolutions/ai-toolkit --skill docs-generatorgit clone --depth 1 https://github.com/asteasolutions/ai-toolkitWhat 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 | $0.00031 | $0.01268 |
| Opus 5 | $0.00015 | $0.00634 |
| Sonnet 5 | $0.00006 | $0.00254 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
docs-generator 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Generator
Sync one markdown file per issue for a chosen project from your connected issue tracker MCP server.
Workflow
Step 0 — Check for existing docs (sync vs. fresh fetch)
Before doing anything, determine whether the project name is known from the user's request.
- If the project name is unknown, skip the manifest check for now. Complete Step 1, then ask the user for the project name before Step 2. Once Step 2 resolves exactly one project, return to this manifest check before Step 3.
- If the project name is known, check whether
docs/[project-name]/_manifest.jsonalready exists. If it does:
- Read
last_synced_atfrom the manifest. - Tell the user:
"Docs for [project] were last synced on [date]. Fetch only issues updated since then, or re-fetch everything?" - If the user picks incremental, pass
updated_after=[last_synced_at]when listing issues in Step 3.- If the incremental fetch returns 0 issues, update
last_synced_atin the manifest to the current time and tell the user:"All docs are up to date — no issues changed since [date]."Then stop.
- If the incremental fetch returns 0 issues, update
- If the user picks full re-fetch, continue with the next unresolved step: Step 1 on a fresh run, or Step 3 if you returned here after Step 2.
If no manifest exists (first run), continue with the next unresolved step: Step 1 on a fresh run, or Step 3 if you returned here after Step 2.
Step 1 — Identify available platforms
Check .mcp.json to see which issue-tracker MCP servers are configured. If only one is found, proceed with it. If multiple are found, ask the user which one to use.
Step 2 — Find the project
Using the chosen platform's MCP tools, search for the project by name. If the search returns no results, tell the user: "No project found matching '[name]'." and stop.
If multiple projects match, list them and ask the user to confirm which one.
Step 3 — Fetch all issues for the project
Fetch all issues regardless of state (open and closed). Paginate until no further pages remain.
What ships with it
2 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 · 86 lines · 31 tokens per session scan A e1f2e97ed971
docs-generator is a skill published in the GitHub repository asteasolutions/ai-toolkit (5 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 1,268 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 2026-08-31.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.