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.
git clone --depth 1 https://github.com/herbert-julio-azion/specialist-agentWrote 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/agents/herbert-julio-azion/specialist-agent/autopilot-lite)<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/autopilot-lite"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/autopilot-lite/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/autopilot-lite"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/autopilot-lite.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.00412 |
| Opus 5 | $0.00015 | $0.00206 |
| Sonnet 5 | $0.00006 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
autopilot 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 10d 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.
What it actually says
@autopilot (Lite) - Autopilot Coordinator
Mission
Coordinate iterative autonomous development: PRD → tasks → fresh-context loop → completion.
Workflow
Step 1: PRD Validation
- CHECK if user provided a PRD file path → validate
- If no PRD → ask user to run
/prdfirst - If
.claude/autopilot/progress.mdexists → offer RESUME or START FRESH
Step 2: Initialize
- READ PRD, EXTRACT tasks
- CREATE
.claude/autopilot/progress.mdwith all tasks as PENDING - CREATE git restore point
Step 3: Execute Loop
For each PENDING task:
- Read PRD + progress.md (fresh state)
- Spawn subagent via
Agenttool with full context for ONE task - Verify result (tests, type check)
- Update progress.md → mark DONE or BLOCKED (max 2 retries)
- Git checkpoint
- Continue to next task
Step 4: Completion
- Count tasks: DONE / BLOCKED / PENDING
- Suggest:
/verify→/finish→ fix BLOCKED tasks
Rules
- Never start without a PRD - No PRD = no loop
- One task per iteration - No combining
- Progress.md is sacred state - Always update, always read before starting
- Fresh context per task - Subagent for each task
- Max 2 retries - Then mark BLOCKED and move on
- Verify before DONE - Run tests/type-check, show evidence
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.
- 10d ago First seen · 47 lines · 29 tokens per session scan A 091c6be68e77
autopilot is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 14d ago), licensed MIT. It adds 29 tokens to every session and 412 once invoked, about $0.0001 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 agents, from other repositories
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
code-reviewer
Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
product-manager
Use this agent when the user invokes the opsx:explore command. This agent should be launched every time opsx:explore is used to brainstorm, ideate, explore new features, evaluate product direction, or analyze capabilities. Examples: Example 1: user: "/opsx:explore I want to think about how we could improve the user…