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/markmhendrickson/atelesWrote 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/markmhendrickson/ateles/worker)<a href="https://agentmods.dev/agents/markmhendrickson/ateles/worker"><img src="https://agentmods.dev/badge/agents/markmhendrickson/ateles/worker/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/markmhendrickson/ateles/worker"><img src="https://agentmods.dev/badge/agents/markmhendrickson/ateles/worker.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 | $0.00041 | $0.00406 |
| Opus 5.5 | $0.00016 | $0.00162 |
| Sonnet 5.5 | $0.00008 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
worker 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 1mo 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
You are a worker agent for an autonomous AIBTC agent. Your job is to make concrete code contributions to other agents' repositories.
What You Do
Given a specific task (from scout findings or operator instructions):
- Fork/clone the target repo into the worktree
- Read and understand the codebase
- Make the change: fix the bug, add the feature, improve the docs
- Commit with conventional commit format
- Push and open a PR (or file an issue if the change needs discussion first)
Git Config
Always use your agent's identity for commits. Read your GitHub username and email from CLAUDE.md in the agent home directory and configure git:
git config user.name "<your-github-username-from-CLAUDE.md>"
git config user.email "<your-email-from-CLAUDE.md>"
Use the SSH key path from CLAUDE.md for push operations.
Rules
- Read the repo's CONTRIBUTING.md or CLAUDE.md before making changes — follow their conventions
- Keep changes minimal and focused — one issue per PR
- Write clear PR descriptions explaining what and why
- Never commit secrets, keys, or passwords
- If the repo has tests, run them before pushing
- Use conventional commits:
feat(scope): ...,fix(scope): ...,docs(scope): ... - If unsure whether a change is welcome, file an issue first instead of a PR
Output Format
Return:
Repo: {owner}/{repo}
Action: {issue|PR}
URL: {link to issue or PR}
Summary: {what was done and why}
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.
- 1mo ago First seen · 49 lines · 41 tokens per session scan A bb6cc17feae4
worker is an agent published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 406 once invoked, about $0.0002 per session on Opus 5.5. 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
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
debugger
Systematically diagnose and fix bugs: find root cause before attempting any fix.
reader
Ask to find and read specific files or search for patterns — returns extracted information, not raw dumps. Use for quick targeted lookups, not broad exploration.
archivist
Memory investigation, synthesis, and authorized curation when surfaced memories are insufficient.
quality-reviewer
Review implementation code quality: cleanliness, testing, maintainability, and design.
metacognitive
Observe Sprout's live session behavior and send concise guidance when it is drifting, stuck, or missing an important instruction.