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/asysta-act/agent-flow/autopilotnpx skills add asysta-act/agent-flow --skill autopilotgit clone --depth 1 https://github.com/asysta-act/agent-flowWrote 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/asysta-act/agent-flow/autopilot)<a href="https://agentmods.dev/skills/asysta-act/agent-flow/autopilot"><img src="https://agentmods.dev/badge/skills/asysta-act/agent-flow/autopilot.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 | $0.00047 | $0.08480 |
| Opus 5 | $0.00023 | $0.04240 |
| Sonnet 5 | $0.00009 | $0.01696 |
| Haiku 4.5 | $0.00005 | $0.00848 |
Grade C, and why
autopilot scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
The lock is a DIRECTORY `.agent-flow/autopilot.lock/` (NOT a file) — `mkdir` is atomic on POSIX and NTFS. A JSON file `owner.json` inside the directory records `{pid, hostname, acquired_at}`. The trap that releases the l How it starts
The opening of the file, as written. The whole thing — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autopilot
Headless dispatcher skill for unattended cron / batch / CI invocation. Reads ### Issue Tracker, ### Feature Workflow (optional) and ### Autopilot (optional) from ## Automation Config, classifies issues into bugs and features, enforces a portable mkdir-based lock, and dispatches agent-flow:fix-bugs or agent-flow:implement-feature per issue sequentially via the Skill tool.
Invoke typically as:
claude -p "Run /agent-flow:autopilot" --dangerously-skip-permissions
or, for safe inspection:
claude -p "Run /agent-flow:autopilot --dry-run" --dangerously-skip-permissions
Reference: docs/guides/autopilot.md for operator onboarding, exit-code matrix, and cron guidance.
Scope & Boundaries
- Dispatcher only — this skill never itself modifies code, writes PRs, or runs tests. Those responsibilities belong to the child skills (
fix-bugs,implement-feature). - Process-local lock —
.agent-flow/autopilot.lock/guards ONE host / filesystem. Multi-host deployments MUST coordinate via DISJOINTBug query/Feature queryfilters per host, or run Autopilot from exactly one host. The plugin emits an INFO line with the hostname on every successful lock acquisition (see Step 3) but does NOT automatically detect cross-host contention. Seedocs/guides/autopilot.md#single-host-operation. - Sequential dispatch — issues are dispatched one at a time. No per-issue parallelism at the Autopilot layer.
- Top-level observability only — Autopilot itself fires NO per-iteration webhooks. Child skills fire their own
pipeline-started/step-completed/pipeline-completedevents per-issue. - Dry-run is a full short-circuit —
Dry run: truemeans no lock, no state.json, no webhook, no dispatch.
Configuration
Follow ../../core/config-reader.md for parsing ## Automation Config from CLAUDE.md.
This skill consumes the following sections:
### Issue Tracker(required):Type,Bug query,State transitions,On start set. TheBug queryrow is the required authoritative input;Feature querylives in### Feature Workflow.### Feature Workflow(optional):Feature query,On start set. Absent section triggers a[WARN]and bug-only mode.### Autopilot(optional): 7 keys below. Absent section = all keys use defaults. Autopilot still runs usingBug queryfrom### Issue Tracker.
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.
- 4d ago First seen · 521 lines · 47 tokens per session scan C 77aa5e5f0e18
autopilot is a skill published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 8,480 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
html-ppt-zhangzara-broadside
OpenDesign's product-launch announcement and press narrative — the headline, the proof points, and the call to action. Built as a decision-grade marketing & GTM deck for press, community, prospects.
geo-prospect
CRM-lite for managing GEO agency prospects and clients. Track leads through the full sales pipeline: Lead → Qualified → Proposal Sent → Won → Lost. Store audit history, notes, deal values, and generate pipeline summaries. Use when user says "prospect", "lead", "client", "pipeline", "crm", "nuovo prospect", "aggiungi…
drug-design
End-to-end drug discovery pipeline orchestration. Deterministic Python script that auto-chains structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering into reproducible workflows.
workflow-creation
Create a new Stencila workflow. Use when asked to create, write, scaffold, or set up a workflow directory or WORKFLOW.md file. Covers workflow discovery, duplicate-name checks, ephemeral workflows, WORKFLOW.md frontmatter, DOT pipeline authoring, goals, agents, branching, composition, and validation.
bump-mthds
Move this repo's exact mthds dependency pin to the latest release on PyPI (or a version you name), re-lock, adapt the engine source to whatever the new release broke, run the checks, and write the CHANGELOG entry — stopping before the commit. Use whenever the user says "bump mthds", "update mthds", "upgrade mthds"…
add-migration
Write a migration ledger entry for a configuration schema change in pipelex, so that a user's existing file can be repaired instead of thrown away. Use when make check-migration-schemas (alias cmig) or make check-ledger (alias cl) refuses a change, when the user says "add a migration", "write the ledger entry", "the…