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/create-testing-plangit 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/create-testing-plan)<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/create-testing-plan"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/create-testing-plan.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 | $0.00029 | $0.01037 |
| Opus 5 | $0.00015 | $0.00518 |
| Sonnet 5 | $0.00006 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
create-testing-plan 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 3d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
the-loop: create-testing-plan $ARGUMENTS
Decide how this work item will be proved, before the task DAG that references it —
the test-planning node, which sits between design and design-approval so the plan
is reviewed with the design it derives from. A slice of /the-loop:work-on; work-on
remains the superset.
Read the the-loop skill and reference/testing.md first. Load
.the-loop/harness-config.yaml, and read every doc registered in
customInstructions.docs — an operator's own testing/environment conventions are exactly
what this artifact should reference rather than restate.
Steps
-
Locate the spec. Resolve
$ARGUMENTStodocs/specs/<id>/and readrequirements.md(orbugfix.md) anddesign.md. The requirements should be locked (status: approved— written by therequirements-approvalgate); the design should be complete (its gated sections filled) but is still a draft, because its human approval comes after this step, at thedesign-approvalgate that reviews — and locks — the pair together (issue-281). Stop only if either is missing or the requirements are unlocked. -
Write
testing-plan.mdfrom${CLAUDE_PLUGIN_ROOT}/skills/the-loop/templates/testing-plan.md(${CLAUDE_PLUGIN_ROOT}= the installed plugin's root; same in Cursor):- Test matrix — one row per candidate testing type (unit, integration, contract,
e2e, UI/visual, snapshot, performance, security/abuse-case, accessibility,
migration, manual exploratory, plus anything else this item needs). Nothing is
mandatory in itself, but every row gets a decision: a type that does not apply is
n/awith a written reason. A trust boundary named indesign.md§Security design must have its negative test named here. - Scenarios & requirement trace — matrix rows → requirement ids → the Gherkin
Scenario:titles the integration tests will carry. - Verification environment — repositories, services, fixtures, bring-up/tear-down
commands. Credentials by reference only (env var name / secret-store key), never
values. Where an operator doc already describes the setup, link the registered
customInstructionsdoc instead of copying it. the-loop runs the project's own commands; it brings no runner of its own. - Evidence plan — what will be captured per activity and where under
docs/specs/<id>/evidence/. For a user-facing surface: screenshots of each verified state, plus an animated capture (GIF) when the behaviour is a flow. - Verification activities — the checklist the
verificationnode ticks. - Verification results — author the heading now holding
_Not yet executed._; the gate treats an empty section as unmet, andverificationfills it later.
- Test matrix — one row per candidate testing type (unit, integration, contract,
e2e, UI/visual, snapshot, performance, security/abuse-case, accessibility,
migration, manual exploratory, plus anything else this item needs). Nothing is
mandatory in itself, but every row gets a decision: a type that does not apply is
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.
- 3d ago First seen · 71 lines · 29 tokens per session scan A 385d5acfec53
create-testing-plan is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 1,037 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
brainstorm
已弃用 - 请改用 superpowers:brainstorming 技能.
execute-plan
已弃用 - 请改用 superpowers:executing-plans 技能.
gaai-audit
Show workspace audit log with filters and optional JSON export.
gaai-ask
Search workspace memory — ranked entries with 1-hop graph context (cognitive guarantee).
gaai-update
Update the GAAI framework or switch AI tool adapter.
gaai-bootstrap
Initialize or refresh project context via Bootstrap Agent.