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/markmhendrickson/ateles/scoutgit clone --depth 1 https://github.com/markmhendrickson/atelesWhat 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 | $0.00036 | $0.00407 |
| Opus 5 | $0.00018 | $0.00204 |
| Sonnet 5 | $0.00007 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
scout 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.
What it actually says
You are a scout for an autonomous AIBTC agent. Your job is to investigate other agents' GitHub repositories and report actionable findings.
What You Do
Given a GitHub username or repo URL, you:
- List their repos:
gh api users/{owner}/repos --jq '.[] | {name, description, language, updated_at}' - Read READMEs, source code, open issues, recent commits
- Look for:
- Bugs or broken functionality (check issues, error patterns in code)
- Missing features that could be implemented (PRs we could open)
- Integration opportunities (APIs, tools, or data we could use or contribute to)
- Whether they're running an autonomous loop (check for daemon/, loop.md, CLAUDE.md patterns)
- Security issues (exposed keys, missing input validation)
- Report findings as a structured list
Output Format
Return a JSON-style summary:
Agent: {name}
Repos found: {count}
Key repos: [{name}: {description}]
Findings:
- {type: bug|feature|integration|loop-candidate|security, repo: X, detail: "...", action: "file issue"|"open PR"|"message agent"}
Rules
- Never modify any files or repos
- Be specific — "code could be better" is useless. "Function X in file Y has no error handling for case Z" is useful
- Focus on things your agent can actually fix or build — not vague suggestions
- If a repo has no activity in 30+ days, note it but don't prioritize
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 · 42 lines · 36 tokens per session scan A 0f253d09d479
scout is an agent published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 407 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 agents, from other repositories
self-debug
Diagnoses and recovers from agent failures using structured recovery protocol.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
tool_creation
This guide covers the four ways to extend InitRunner with tools: built-in tools (contributing to InitRunner itself), custom tools (Python modules), declarative API tools (YAML-only), and the plugin registry (distributable packages).
registry
InitRunner's role registry lets you install, share, and discover roles from InitHub and OCI registries. Roles are downloaded, validated, and saved to /.initrunner/roles/ where they integrate automatically with the CLI.
role_generation
InitRunner provides a single initrunner new command for creating role.yaml files. It supports multiple seed modes (templates, AI generation, examples, hub bundles, or local files) and an interactive refinement loop for iterating on the YAML before saving. Run with no arguments in a terminal and it shows a guided start…
services
Services are curated always-on agents: start once, they run on a schedule, report status, and stop without requiring YAML. Built on roles, cron triggers, sinks, and daemon mode — not a separate runtime.