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/madarauchiha-314/the-loop/work-ongit 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/work-on)<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/work-on"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/work-on.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 | $0.00040 | $0.03284 |
| Opus 5 | $0.00020 | $0.01642 |
| Sonnet 5 | $0.00008 | $0.00657 |
| Haiku 4.5 | $0.00004 | $0.00328 |
Grade A, and why
work-on 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 5d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
the-loop: work-on $ARGUMENTS
Drive a single work item end-to-end with minimal/no human intervention, following the
Kiro-style 3-phase spec workflow (https://kiro.dev/docs/specs/). Load
.the-loop/harness-config.yaml first, then read every custom instruction doc it registers
(customInstructions.docs, in order; missing docs per customInstructions.onMissing)
and honor them throughout — they carry the operator's conventions and styles
(reference/instructions.md). Run the-loop instructions alongside that read, so a
registration that fails to resolve surfaces instead of quietly contributing nothing. Apply any per-task overrides from the work item's
front-matter. Specs live in <workflow.specDir>/<id>/ (default docs/specs/<id>/).
work-on is the superset. The same flow is also exposed as granular commands you can
run one step at a time: /the-loop:brainstorm (optional) → /the-loop:new-requirement →
/the-loop:create-ticket → /the-loop:create-design → /the-loop:create-tasks-plan →
/the-loop:execute-tasks → /the-loop:finish-tasks, with /the-loop:work-status <id> to
report progress. work-on runs them end-to-end; reach for the granular commands to start
pre-ticket (or with a brainstorm) or to drive a single phase.
Before acting, read the the-loop skill and its reference files for the full rules:
reference/workflow.md (phases, reviews, DAG), reference/context.md (checkpoint-then-
reset window management), reference/tooling.md (which commands to run),
reference/collaboration.md (who to involve, paper trail),
reference/observability.md. The summary below is the procedure; the references are the
detail — do not lose it.
Phase state machine
Keep the work item's phase label in the ticketing system in sync at every
transition (label = <workflow.phaseLabelPrefix><phase>, e.g. loop:design), and
mirror it in the execution log's phase front-matter (brainstorming is optional — enter
it only when the work needs a scratchpad; otherwise start at requirements-definition):
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.
- 5d ago First seen · 200 lines · 40 tokens per session scan A e592b359e07a
work-on is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 3,284 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
receipts
Find the receipt. A dated line, or it did not happen.
ship
Seen on their staging, then live. Rollback you have run.
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.
import
Import a shared context bundle, or take a teammate's newer copy of one you already have.
duck-off
Turn off Rubber Duck mode and answer normally.
extensions
Show what the connected context expects to reach, and whether this machine provides it.