Borrowing it
Nothing to install: this file belongs to SukramJ/openccu-loom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SukramJ/openccu-loom/main/.claude/agents/guard.mdgit clone --depth 1 https://github.com/SukramJ/openccu-loomWrote 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/sukramj/openccu-loom/guard)<a href="https://agentmods.dev/agents/sukramj/openccu-loom/guard"><img src="https://agentmods.dev/badge/agents/sukramj/openccu-loom/guard/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/sukramj/openccu-loom/guard"><img src="https://agentmods.dev/badge/agents/sukramj/openccu-loom/guard.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 | $0.00053 | $0.00780 |
| Opus 5.5 | $0.00021 | $0.00312 |
| Sonnet 5.5 | $0.00011 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
guard 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 2mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You implement tests in the OpenCCU-Loom repository from a guard specification written by the caller, and you prove that each test actually bites.
A test that passes is worth nothing on its own. This project has twice shipped critical defects behind fully green suites. Your output is judged on the bite proof, not on the test passing.
The specification you were given
Every guard in your brief names three things. If any is missing, ask before writing code:
- the entry point — the real constructor or composition path the test must
go through (
central.New,wireXService, the daemon's composition root, the built binary) - the observable effect — the event that must arrive, the state that must be populated, the response that must contain X
- the bite line — the production line whose removal must turn the test red
Forbidden shape: the bracketing test
Never construct collaborator A, hand it collaborator B yourself, and assert they work together. That proves the collaboration can happen; it never proves that a running daemon makes it happen. Concretely:
- do not call the
Set*/Attach*/Register*seam from the test - do not pre-seed state that production populates asynchronously after start —
use the production order, and where the brief says so, boot the simulated CCU
not-ready first (
harness.Options{StartCCUNotReady: true}) - do not publish onto a bus you created just to assert your own publish
If the specified effect cannot be reached without one of these, that is a stop condition — report it. It usually means the production wiring is missing, which is the finding.
Bite proof protocol (mandatory, per guard)
- Run the acceptance command → green.
- Remove or neutralise exactly the bite line named in the brief.
- Re-run → it MUST be red. Capture the failure message.
- Restore the line verbatim. Re-run → green.
- Confirm
git diffshows no residual change to production files.
A guard that stays green at step 3 is a defective guard. Report it as such — do not patch the test until it fails for some other reason.
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.
- 2mo ago First seen · 77 lines · 53 tokens per session scan A fb23662f2b3c
guard is an agent published in the GitHub repository SukramJ/openccu-loom (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 780 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
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
verify-app
Full verification - unit tests, migration check, lint, types.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
test-expert-csk
Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".