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.
git clone --depth 1 https://github.com/MadaraUchiha-314/the-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/commands/madarauchiha-314/the-loop/contribute-to)<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/contribute-to"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/contribute-to/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/commands/madarauchiha-314/the-loop/contribute-to"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/contribute-to.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 | $0.00038 | $0.00948 |
| Opus 5 | $0.00019 | $0.00474 |
| Sonnet 5 | $0.00008 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
contribute-to 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 9d 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.
the-loop: contribute-to $ARGUMENTS
Make a scoped intervention in a work item the-loop does not own: an issue or pull
request that already exists, is already in progress, and may have been produced by a
bespoke process — do not assume any spec-chain artifact exists. The process is the
contribution loop (pdlc-contribution-loop), the third shipped graph; ask
the-loop check <id> / the-loop graph show where the item stands rather than
re-deriving it. Load .the-loop/harness-config.yaml first and honor every custom
instruction doc it registers, exactly as work-on does. If the file does not
exist, the repository has not adopted the-loop: run on the defaults (specs at
docs/specs/), treat the spec tree as working state only — the runtime excludes it
from git; never commit or push it, the contribution PR carries only the
intervention — and let the publish-artifact hook post the plan and verification
results to the thread, the review surface such a repository offers.
Before acting, read the the-loop skill and its reference files — this command
follows all the same rules (paper trail, self-marked comments, reviews, context
management); only the node set differs.
What is different from work-on
-
The goal is the human's, and it is mandatory. The loop's first node,
goal-definition, isrequired: true: it waits until an authorized user has stated, in one comment:Goal: <what the-loop should accomplish here> Success criteria: - [ ] <how we will know it worked>Never invent, infer, or "helpfully complete" a goal — if none is stated, the gate posts the format once and waits. The frozen criteria are the definition of done.
-
One artifact, not four. The planning nodes (
context-intake,scoped-plan) author a single<workflow.specDir>/<id>/contribution.md— goal, success criteria, context, approach, verification plan — from the bundledcontribution.mdtemplate. Requirements-and-design thinking still happens; it just lands in sections, not files. Leave it a draft atscoped-planand iterate it with the human atplan-approval— the gate locks it on the human's one approval (issue-281); never setstatus: approvedyourself.
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.
- 9d ago First seen · 72 lines · 38 tokens per session scan A 24e72d54f3ac
contribute-to is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 948 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 commands, from other repositories
workspace-sync
(Workspace) Cross-repo "what changed while I was away" — discover, reconcile, and report.
pr
Open the PR for a verified story (In Review → In PR), body filled from the ledger.
sync-main
Reconcile git main vs. the ledger — what merged while you were away (read-only).
init-workspace
(Workspace) Set up the optional multi-repo orchestrator — Registry + Config.
start-us
Start a story — dependency-gate, move To Do → In Progress, offer the branch.
publish
Publish oh-my-opencode to npm via GitHub Actions workflow.