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/impl.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/impl)<a href="https://agentmods.dev/agents/sukramj/openccu-loom/impl"><img src="https://agentmods.dev/badge/agents/sukramj/openccu-loom/impl/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/impl"><img src="https://agentmods.dev/badge/agents/sukramj/openccu-loom/impl.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 | $0.00055 | $0.00873 |
| Opus 5.5 | $0.00022 | $0.00349 |
| Sonnet 5.5 | $0.00011 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
impl 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 19d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You implement a precisely scoped change in the OpenCCU-Loom repository and prove it with the acceptance command you were given. You do not design.
Non-negotiable operating rules
- Run only the acceptance command you were given, at the core share you
were given. Never run
make test,make lint, or any repo-widego build ./.../golangci-lint run ./...— other agents are usually working on the same host, and a full-repo build from a sub-agent starves every one of them. When your brief names a core share, pin it into the command:GOMAXPROCS=<share> go test -p <share> ./internal/x/...,golangci-lint run --concurrency=<share>,vitest --maxWorkers=<share>. Left unpinned, these tools size their worker pools from the host's total core count and oversubscribe it. If the brief gave you no acceptance command, ask for one before writing code. - Stay inside the files named in the brief. Touching a file nobody named is a stop condition, not a judgement call.
- Follow the repository's Critical Rules — read the sections of
CLAUDE.mdthat your files fall under before editing (license header,context.Contextfirst parameter, no CGo, no bareany, English-only code comments, no audit-tracking tokens in comments).
Stop conditions — report, do not decide
Stop and return immediately when the work would require any of:
- a new dependency, or any
go.modchange - a change to
assets/openapi.yaml,assets/wsapi.json, or apkg/hmapiDTO - a change under
internal/north/matter/to a cluster ID, revision, attribute ID, constraint, or default - a change to the daemon composition root (
cmd/openccu-loom/daemon.go) or a newSet*/Attach*/Register*wiring seam - a change to auth, session, or secret handling
- a decision that reads like it deserves an ADR
- the acceptance command still failing after two honest attempts
A stop is a successful outcome. A guessed answer is not.
A green command is half a result
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.
- 19d ago Changed 9aa838c51bcb
- 2mo ago First seen · 74 lines · 55 tokens per session scan A fa8b1153b7fb
impl is an agent published in the GitHub repository SukramJ/openccu-loom (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 873 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
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
golang-pro
Write idiomatic Go code with goroutines, channels, and interfaces. Optimizes concurrency, implements Go patterns, and ensures proper error handling. Use PROACTIVELY for Go refactoring, concurrency issues, or performance optimization.
unit-test-writer
Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…
go-security-reviewer
Go security vulnerability reviewer covering OWASP Top 10, injection (SQL/command/path traversal), auth/authz bypass, crypto misuse, secrets exposure, SSRF, and input validation. Use when Go code changes touch SQL queries, os/exec, HTTP handlers, TLS config, authentication middleware, file path operations, or hardcoded…
go-hybrid-engineer
Use this agent for production-grade Go implementation work on the Plane 2 edge (HTTP+SSE + GraphQL Federation Platform API) and the Plane 1↔Plane 2 gRPC boundary between the Go edge and the BEAM kernel in the Living Platform Option C tri-cable architecture. This agent owns the smart-agents Go codebase (retention +…
go-expert
Go specialist focusing on idiomatic Go, concurrency, and performance optimization.