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 skills/william-london/ownframework-loop/reviewnpx skills add william-london/ownframework-loop --skill reviewgit clone --depth 1 https://github.com/william-london/ownframework-loopWrote 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/william-london/ownframework-loop/review)<a href="https://agentmods.dev/skills/william-london/ownframework-loop/review"><img src="https://agentmods.dev/badge/skills/william-london/ownframework-loop/review.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00509 |
| Opus 5 | $0.00017 | $0.00254 |
| Sonnet 5 | $0.00007 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
review 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 4d 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.
This is a copy
94% identical to review — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/of-loop:review - one bounded review pass
The parent is a thin coordinator. It does not engineer source and does not own branch/worktree/state identity.
Fast paths (single source of truth)
| State | Action |
|---|---|
| APPROVED / BLOCKED / STOPPED | STOP |
| AWAITING_APPROVAL / READY_TO_START | WAIT - builder owns first start |
| READY_TO_BUILD / BUILDING / CHANGES_REQUESTED | WAIT - no reviewable receipt yet |
| READY_FOR_REVIEW / replayed REVIEWING | REVIEW - proceed |
Pre-start semantics
For an unstarted run with state AWAITING_APPROVAL / READY_TO_START:
- Reviewer WAITS. The builder owns first execution start.
- Reviewer does NOT create the execution seal independently.
- Reviewer does NOT call ofloop build claim.
- Reviewer does NOT issue approval or token.
After the builder creates a build receipt and transitions state to READY_FOR_REVIEW or CHANGES_REQUESTED, the reviewer proceeds with normal exact-SHA review.
Pass responsibilities
- Re-prove current packet bytes and execution binding.
- Claim via ofloop review claim --actor reviewer. A replayed REVIEWING claim is the same pass and MUST NOT increment budget.
- Run ofloop review prepare .
- Optionally materialize reviewer scratch via ofloop review assessment-skeleton.
- Run ofloop review finalize .
- Emit ofloop review marker .
Prohibitions
No raw worktree creation or removal; no direct state/receipt/verdict writes; no scope/budget widening; no push, merge, deploy, publish, remote creation, or external effect.
Scheduling
Canonical unattended scheduling is ofloop supervisor enqueue <repo> <run-id>.
This skill represents one pass and may be invoked through a host adapter for
foreground/debug work (Claude: /of-loop:review <run-id>). It is not the
durable execution clock.
The operator supplies no cadence, claim, preparation, assessment-skeleton, finalizer, or approval commands.
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.
- 4d ago First seen · 59 lines · 35 tokens per session scan A d2fc814000af
review is a skill published in the GitHub repository william-london/ownframework-loop (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 35 tokens to every session and 509 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to review, differing in 3 lines, and is treated as a copy.
Other skills, from other repositories
akg-agents
代理执行 AKG 算子任务。先检查固定仓库与分支；若 /.akg/checkenv.md 不存在则强制 FULLSETUP=true；忽略所有 akgcli 检查和使用；后端代码生成直接执行 runworkflow.py --workflow kernelgen。.
openJiuwen-DeepSearch
知识增强型深度检索与深度研究，支持查询规划、信息收集、理解反思、研究报告生成等多 Agent 协同。使用场景：金融分析研报、学术与政策研究、企业级深度搜索等复杂推理任务，可以生成Markdown、Doc和Html格式的研究报告。每次使用该技能之前都先完整阅读一遍SKILL.md学习技能。.
my-custom-skill
Example custom agent skill — a template to get started.
to-issues
Decompose a PRD and/or SPEC into implementable, vertically-sliced Issues with real blocking edges, then create them in your chosen platform (GitHub or Local). Use after /prd (and optionally /prd-to-spec) to turn requirements into agent-ready tickets. Triggers on: create issues, to-issues, 创建issue, 拆解issue, 生成卡片, 创建卡片…
economic-reasoning
Economic decision-making for agents in EconomySpace. Activate when the agent observes currency, prices, income, tax, or trading opportunities to make informed financial decisions.
care.basic
Offer basic care check-ins for neighbors.