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 commands/jackofall1232/l00prite/resume-loopgit clone --depth 1 https://github.com/jackofall1232/l00priteWrote 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/commands/jackofall1232/l00prite/resume-loop)<a href="https://agentmods.dev/commands/jackofall1232/l00prite/resume-loop"><img src="https://agentmods.dev/badge/commands/jackofall1232/l00prite/resume-loop.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 | $0.00000 | $0.01094 |
| Opus 5 | $0.00000 | $0.00547 |
| Sonnet 5 | $0.00000 | $0.00219 |
| Haiku 4.5 | $0.00000 | $0.00109 |
Grade A, and why
resume-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 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume Loop Prompt
Path convention: every
.l00prite/path in this prompt is relative to the protocol root — the directory that contains the.l00prite/folder. In a project scaffolded by build-loop that is thel00prite/directory at the repo root (memory atl00prite/.l00prite/); in the l00prite source repo it is the repo root itself.
You are resuming a l00prite-managed project. Treat .l00prite/ as the shared source of truth across Claude, Codex, GPT, Gemini, and future agents.
This prompt performs one supervised loop iteration: one smallest useful step, verified,
persisted, then stop. For an autonomous multi-iteration run that continues until a run
boundary, use .l00prite/prompts/execute-loop.md instead — it requires its own pre-flight
confirmation before starting.
Required context read
Before changing files, read:
.l00prite/blueprint.md.l00prite/ledger.md.l00prite/memory.md.l00prite/constraints.md.l00prite/failures.md.l00prite/todos.md.l00prite/state.json.l00prite/heartbeat.json.l00prite/lock.json
Lock check (required before any write)
- Read
.l00prite/lock.jsonbefore mutating any protected path (ledger.md,memory.md,state.json,heartbeat.json,failures.md,todos.md,events/,reviews/,sessions/). - If
statusisunlocked,released, orexpired, acquire the lock: setstatus: "active", a newlock_id,owner_agent,owner_session,acquired_at,expires_at(acquired_at+ttl_seconds), andpurpose. - If
statusisactive, not expired, and owned by a different agent or session, do not write. Stop and report the lock as a blocker instead of proceeding. - If
statusisactive, not expired, and already owned by you (matchingowner_agent/owner_session), continue writing — you do not need to re-acquire before each write within the same run. - If
statusisactivebutexpires_athas passed, orstatusis explicitlyexpired, treat it as stale: you may reclaim it (acquire as above), but record aledger.mdentry noting the reclaimedlock_idand why it was judged stale. - If a step is likely to run longer than
ttl_seconds(e.g. a slow test suite), refreshexpires_atpartway through rather than letting a still-running step look stale. - Release the lock (
status: "released") before stopping, once your memory updates are complete. See.l00prite/LOCKING.mdfor the full rules.
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 · 73 lines · 0 tokens per session scan A 08fe677200ca
resume-loop is a command published in the GitHub repository jackofall1232/l00prite (9 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,094 tokens. 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 commands, from other repositories
mach12:issue-implement
Implement a specific stage of an issue's implementation plan.
mach12:gh-assign
Assign the current user to one or more GitHub issues, handling existing assignees.
mach12:gh-issue-read
Read a GitHub issue's title, body, and all comments; optionally locate an HTML-marker comment.
mach12:gh-sub-issues
Detect sub-issues of a GitHub issue using the two-strategy approach (API, then body-parse).
init
Initialize dev-flow project — scan current state, create/align .dev-doc, update agent instruction file.
issue
DOCROOT obtained via dow status --field docroot.