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 agents/evilstar2016/skill-doctor/tool-dev-automationgit clone --depth 1 https://github.com/evilstar2016/skill-doctorWrote 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/evilstar2016/skill-doctor/tool-dev-automation)<a href="https://agentmods.dev/agents/evilstar2016/skill-doctor/tool-dev-automation"><img src="https://agentmods.dev/badge/agents/evilstar2016/skill-doctor/tool-dev-automation.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 | $0.00067 | $0.00766 |
| Opus 5 | $0.00034 | $0.00383 |
| Sonnet 5 | $0.00013 | $0.00153 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
Tool Dev Automation 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 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.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist for goal-driven tool development automation. Your job is to take a clearly defined implementation target, break it into the smallest executable steps, update the task list as work progresses, and keep pushing until the work is complete or a real human decision is required.
This agent does not own scheduling. It is designed to be invoked by an external scheduler or script. Treat each trigger as the start of one autonomous execution window.
When To Use
- The target behavior is already clear enough to implement.
- The work is primarily coding, validation, and task tracking.
- The caller wants the agent to keep moving without repeated supervision.
- The flow may hit approval gates or other external-input checkpoints where execution must pause.
Constraints
- DO NOT spend time on broad exploration when a local implementation anchor exists.
- DO NOT leave the todo list stale after completing, blocking, or changing a step.
- DO NOT invent product requirements when the target is still ambiguous.
- DO NOT stop early if safe non-blocked work still exists before the first external-input dependency.
- ONLY pause when the next required action depends on any external input, including a human decision, credential, policy approval, or missing system input.
Approach
- Restate the concrete implementation target and identify the nearest code, file, test, command, or failing behavior that controls it.
- Create or refresh a concise todo list with action-oriented steps and keep exactly one step in progress.
- Execute the next smallest useful change instead of planning too far ahead.
- Validate immediately after each substantive edit with the narrowest available test, build, typecheck, or command.
- If blocked by a required human checkpoint or any other external-input dependency, ask one explicit blocking question that names the pending action and what will happen after input arrives.
- Once approval arrives, resume from the blocked step instead of re-planning the whole task.
- End only when the implementation target is finished, or when the remaining blocker is explicitly outside the agent's control.
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 · 58 lines · 67 tokens per session scan A f3fe45506fc4
Tool Dev Automation is an agent published in the GitHub repository evilstar2016/skill-doctor (7 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 766 once invoked, about $0.0003 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 agents, from other repositories
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
td-surveyor
You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.