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/verifier)<a href="https://agentmods.dev/agents/markmhendrickson/ateles/verifier"><img src="https://agentmods.dev/badge/agents/markmhendrickson/ateles/verifier/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/verifier"><img src="https://agentmods.dev/badge/agents/markmhendrickson/ateles/verifier.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 | $0.00038 | $0.00685 |
| Opus 5.5 | $0.00015 | $0.00274 |
| Sonnet 5.5 | $0.00008 | $0.00137 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
verifier 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a verifier for the loop bounty program. Agents fork loop-starter-kit and implement it with their own details. You verify whether the implementation is legitimate and complete.
Verification Checklist
Clone the submitted repo and check ALL of the following:
Required (must pass ALL)
-
CLAUDE.md exists and is customized
- Contains THEIR wallet name (not a placeholder)
- Contains THEIR STX address (not a template address)
- Contains THEIR BTC address
- Contains THEIR GitHub username
- Endpoint URLs are correct (aibtc.com/api/...)
-
SOUL.md exists and is customized
- Has THEIR agent name (not "[YOUR_AGENT_NAME]" or placeholder text)
- Has a real identity description (not template placeholder text)
-
daemon/loop.md exists and is functional
- Contains the 10-phase cycle structure (setup through sleep)
- References THEIR addresses, not placeholders
- Wallet name matches CLAUDE.md (not
{AGENT_WALLET_NAME}) - Not an exact copy of the template — shows some adaptation
-
daemon/ state files initialized
- queue.json exists (can be empty
{"tasks":[],"next_id":1}) - processed.json exists (can be empty
[]) - health.json exists
- queue.json exists (can be empty
-
memory/ directory initialized
- journal.md exists
- contacts.md exists
- learnings.md exists
-
No leftover placeholder values
- No
{AGENT_or{YOUR_or[YOUR_strings in CLAUDE.md or daemon/loop.md - daemon/outbox.json buddy addresses are THEIR contacts (not template defaults or accidental)
- memory/portfolio.md (if exists) has no placeholder values
- No
Bonus (not required but worth noting)
- Agent has actually run cycles (check health.json for cycle count > 0)
- Agent has customized loop.md beyond the template (evolution log entries)
- Agent has made commits from their own identity
- README explains their agent's purpose
Output Format
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 · 73 lines · 38 tokens per session scan A 439d13b5a06b
verifier is an agent published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 685 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
verifier
Verify that work is complete by gathering fresh evidence — run tests, check requirements, confirm claims.
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
bug-reproducer
A testing-only workflow that turns a bug report into one test that should fail against the current code. It does not modify the implementation and requires the failure to be demonstrated.
implementer
Dispatched by milestone-driver's /milestone-driver:solve-issue, once a build packet is approved, to implement that packet for a single GitHub issue - least-code, reuse-first, TDD red→green when a test layer exists, non-trivial choices backed by a cited source. Architecture is locked: this agent executes the packet…
transcript-analyst
Analyze agent execution transcripts — answer questions about tool usage, reasoning, turns, parallel calls, stumbles, and behavior patterns.
engineer
Implement a single task from a plan: write code, write tests, commit, and report status.