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 skills add william-london/ownframework-loop --skill of-loop-buildgit 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/of-loop-build)<a href="https://agentmods.dev/skills/william-london/ownframework-loop/of-loop-build"><img src="https://agentmods.dev/badge/skills/william-london/ownframework-loop/of-loop-build.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 5.1 | $0.00042 | $0.00704 |
| Opus 5 | $0.00021 | $0.00352 |
| Sonnet 5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
build 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 7d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/of-loop:build - one bounded build or repair 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 |
| READY_FOR_REVIEW / REVIEWING | WAIT |
| AWAITING_APPROVAL / READY_TO_START | STARTABLE; invoke ofloop build claim; first claim may auto-seal |
| READY_TO_BUILD / CHANGES_REQUESTED / replayed BUILDING | proceed normally |
Internal state AWAITING_APPROVAL is preserved for compatibility. The operator-facing meaning is READY_TO_START (the run is startable; no approval ceremony is required).
Substantial passes (F-5-01 v0.3.7)
A bounded build pass is not required to be minimal. When the must-fix surface, scope, or refactor cut spans multiple files, the builder may produce a coherent substantial pass. The operator MUST NOT collapse or thin the change set to keep the pass small.
First-start execution seal (v0.5.x)
The first ofloop build claim invocation on an unstarted run creates the immutable execution seal: binding_method=build_start, binding_kind=execution_seal. The operator first build claim IS the authorization to execute the exact bounded packet locally.
No prior human approval. No confirmation token. No program init. No legacy sealing command. No ofloop loop run.
Pass responsibilities
- Re-prove current packet bytes and execution binding.
- Claim via ofloop build claim --actor builder. A replayed BUILDING claim is the same pass and MUST NOT increment budget.
- Run ofloop build prepare . This is the sole owner of baseline, candidate branch, checkpoint/work-unit identity, builder worktree, and pass-scoped result path.
- Run ofloop build agent-skeleton without --overwrite. Fresh claims get a new pass path; replayed claims retain the same path.
- Invoke one fresh of-builder with exactly the prepared context.
- The agent engineers only in the prepared worktree and fills only the exact pass-scoped semantic result.
- Call ofloop build finalize <agent_result_path>.
- Emit ofloop build marker .
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.
- 7d ago First seen · 72 lines · 42 tokens per session scan A fb1c24c918e0
build is a skill published in the GitHub repository william-london/ownframework-loop (0 stars, last pushed 5d ago), licensed Apache-2.0. It adds 42 tokens to every session and 704 once invoked, about $0.0002 per session on Opus 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 skills, from other repositories
mine-plan-review
Strictly review one implemented repository plan against AGENTS.md, architecture, the immutable plan, implementation commits, real runtime behavior, verification evidence, and downstream contracts. Use when the user invokes the host-specific mine-plan-review skill with a plan path, asks whether a plan can be accepted…
review
A code-review skill that compares implemented code with its specification and plan, then writes a structured report of missing work, bugs, and risks.
review
Review all uncommitted changes against project standards before committing.
review-pr
Review a pull request for quality, security, and correctness.
k-review
An independent review of frozen Git base and head versions, checking both the written specification and project standards.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.