Borrowing it
Nothing to install: this file belongs to gevico/cosim-gpu. 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/gevico/cosim-gpu/main/.agents/skills/cosim-gpu-rlcr-loop/SKILL.mdgit clone --depth 1 https://github.com/gevico/cosim-gpuWrote 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/skills/gevico/cosim-gpu/cosim-gpu-rlcr-loop)<a href="https://agentmods.dev/skills/gevico/cosim-gpu/cosim-gpu-rlcr-loop"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-rlcr-loop/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/skills/gevico/cosim-gpu/cosim-gpu-rlcr-loop"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-rlcr-loop.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 | $0.00978 |
| Opus 5.5 | $0.00016 | $0.00391 |
| Sonnet 5.5 | $0.00008 | $0.00196 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
cosim-gpu-rlcr-loop 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cosim RLCR Loop
Run iterative implementation or debugging after cosim-gpu-flow-plan. This
skill owns round state, acceptance criteria, interruption recovery, and the
order of build, test, and review gates. Independent reviewer rules live in
../cosim-gpu-review/references/review/independent-review-contract.md; read
that file before each review gate.
Required Inputs
artifacts/<task-slug>/plan.md- frozen acceptance criteria
- chosen domain skill for the technical work
- build and provenance gate from
cosim-gpu-build - current
HEADrecorded as the source-edit base
If there is no plan, run cosim-gpu-flow-plan first.
Artifact Layout
artifacts/<task-slug>/rlcr/
├── goal-tracker.md
├── round-001-summary.md
├── round-001-review.md
└── final-summary.md
Logs, review briefs, verdicts, and provenance stay in the task workspace under
logs/, reviews/, tests/, or existing artifact paths.
Goal Tracker
Maintain rlcr/goal-tracker.md:
# Goal Tracker
## Immutable
- Goal:
- Acceptance Criteria:
## Mutable
- Active round:
- Completed:
- Remaining:
- Deferred with reason:
- Decision log:
Do not change the immutable section without explicit human approval.
Round Loop
Repeat until all acceptance criteria pass and the independent review stop rule is satisfied.
Stop rules apply in this order:
- user-supplied stop rule in
plan.mdorgoal-tracker.md - frozen acceptance criteria plus required evidence gates
- default convergence: two consecutive independent reviews with no new
BLOCKERorMAJORfindings
Each round:
- Select the smallest coherent objective that advances a named acceptance criterion.
- Re-read current evidence, acceptance criteria, source base, and pending findings.
- For bug/debug tasks, write at least two mutually exclusive hypotheses to
scratch/hypotheses.mdbefore source edits. - Implement or investigate using the selected domain skill.
- After any source change, treat prior test rows as non-final.
- Run the standard incremental build and relevant test rows.
- Write
rlcr/round-NNN-summary.mdwith commands, artifacts, verdicts, source base, and remaining work. - Run the independent review gate through
cosim-gpu-revieworcosim-gpu-codex-review, following the shared review contract. - Audit findings, fix accepted in-scope issues, and defer wider redesigns with reasons.
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 First seen · 134 lines · 41 tokens per session scan A cfe8f9b303cb
cosim-gpu-rlcr-loop is a skill published in the GitHub repository gevico/cosim-gpu (95 stars, last pushed 4d ago), licensed Apache-2.0. It adds 41 tokens to every session and 978 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 2026-10-10.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.