Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadaraUchiha-314/the-loop/plugin install 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/new-requirement)<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/new-requirement"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/new-requirement/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/new-requirement"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/new-requirement.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 | $0.00027 | $0.00800 |
| Opus 5 | $0.00014 | $0.00400 |
| Sonnet 5 | $0.00005 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
new-requirement 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
the-loop: new-requirement $ARGUMENTS
Draft a requirements spec for work that has no ticket yet. Some work starts as an
idea; the-loop lets you define the requirements first, then mint the ticket from them
(/the-loop:create-ticket). This is a slice of /the-loop:work-on (Phase 1 only) —
work-on remains the superset.
If the idea was first explored in a brainstorm.md (the optional Phase 0 root
artifact from /the-loop:brainstorm), this command converts that locked brainstorm
into requirements rather than starting from a blank page.
Read the the-loop skill and reference/workflow.md first (phases, EARS, reviews).
Steps
-
Create or reuse the temporary spec folder. Slugify
$ARGUMENTS→<slug>and usedocs/specs/draft-<slug>/(reuse it if/the-loop:brainstormalready created it).draft-*folders are the-loop's convention for a spec that has no ticket yet;/the-loop:create-ticketrenames it todocs/specs/<id>/. -
Convert from a brainstorm if present. If a sibling
brainstorm.mdexists in the folder, read it and derive the requirements from its locked direction — its chosen option becomes the introduction, its working hypothesis + hand-off become the user stories, and its resolved constraints become acceptance criteria. Do not proceed off an unlocked brainstorm (statusnotapproved): lock it first, or say so and stop. Everything the brainstorm considered-and-rejected stays inbrainstorm.md(the record); only the carried-forward direction lands inrequirements.md. -
Write
requirements.mdfrom${CLAUDE_PLUGIN_ROOT}/skills/the-loop/templates/requirements.md(${CLAUDE_PLUGIN_ROOT}= the installed plugin's root; same in Cursor): introduction, user stories, and EARS acceptance criteria (WHEN <event> THEN the system SHALL <response>), plus the Security considerations section (threat-model-lite: untrusted actors, trust boundaries, abuse cases, fail-closed —security.threatModel.required; "no new attack surface" is written and justified, seereference/security.md). Set front-matterphase: requirements-definition,status: draft,workItem: draft-<slug>, and the requiredcollaborators.
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 · 58 lines · 27 tokens per session scan A 028567f53c18
new-requirement is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 800 once invoked, about $0.0001 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
receipts
Find the receipt. A dated line, or it did not happen.
ship
Seen on their staging, then live. Rollback you have run.
devils-advocate
Stress-test an idea, plan, or decision by arguing against it honestly, to find the flaws before reality does.
estimate-work
Estimate a task or project honestly, by decomposing it, surfacing unknowns, and giving a range not a false point.
break-down-task
Break a goal into an ordered, actionable plan with dependencies and a clear first step.
bug-report-triage
Turn a vague bug report into a structured, actionable ticket with severity and next steps.