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/loulanyue/spec-kit-zhWrote 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/loulanyue/spec-kit-zh/selftest)<a href="https://agentmods.dev/commands/loulanyue/spec-kit-zh/selftest"><img src="https://agentmods.dev/badge/commands/loulanyue/spec-kit-zh/selftest/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/loulanyue/spec-kit-zh/selftest"><img src="https://agentmods.dev/badge/commands/loulanyue/spec-kit-zh/selftest.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 | $0.00010 | $0.00537 |
| Opus 5.5 | $0.00004 | $0.00215 |
| Sonnet 5.5 | $0.00002 | $0.00107 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade C, and why
selftest scanned grade C with 1 finding 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 14d 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.
Nullifies safety policieshighAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
Then, simulate adding the extension by installing it from its catalog download URL, which should bypass the restriction. This is a copy
100% identical to selftest — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extension Self-Test: $ARGUMENTS
This command drives a self-test simulating the developer experience with the $ARGUMENTS extension.
Goal
Validate the end-to-end lifecycle (discovery, installation, registration) for the extension: $ARGUMENTS.
If $ARGUMENTS is empty, you must tell the user to provide an extension name, for example: /speckit.selftest.extension linear.
Steps
Step 1: Catalog Discovery Validation
Check if the extension exists in the Spec Kit catalog.
Execute this command and verify that it completes successfully and that the returned extension ID exactly matches $ARGUMENTS. If the command fails or the ID does not match $ARGUMENTS, fail the test.
specify extension info "$ARGUMENTS"
Step 2: Simulate Installation
First, try to add the extension to the current workspace configuration directly. If the catalog provides the extension as install_allowed: false (discovery-only), this step is expected to fail.
specify extension add "$ARGUMENTS"
Then, simulate adding the extension by installing it from its catalog download URL, which should bypass the restriction.
Obtain the extension's download_url from the catalog metadata (for example, via a catalog info command or UI), then run:
specify extension add "$ARGUMENTS" --from "<download_url>"
Step 3: Registration Verification
Once the add command completes, verify the installation by checking the project configuration.
Use terminal tools (like cat) to verify that the following file contains a record for $ARGUMENTS.
cat .specify/extensions/.registry/$ARGUMENTS.json
Step 4: Verification Report
Analyze the standard output of the three steps. Generate a terminal-style test output format detailing the results of discovery, installation, and registration. Return this directly to the user.
Example output format:
============================= test session starts ==============================
collected 3 items
test_selftest_discovery.py::test_catalog_search [PASS/FAIL]
Details: [Provide execution result of specify extension search]
test_selftest_installation.py::test_extension_add [PASS/FAIL]
Details: [Provide execution result of specify extension add]
test_selftest_registration.py::test_config_verification [PASS/FAIL]
Details: [Provide execution result of registry record verification]
============================== [X] passed in ... ==============================
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.
- 14d ago First seen · 70 lines · 10 tokens per session scan C 93f33139a3da
selftest is a command published in the GitHub repository loulanyue/spec-kit-zh (337 stars, last pushed 13d ago), licensed MIT. It adds 10 tokens to every session and 537 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it C with 1 finding (nullifies safety policies). It is 100% identical to selftest, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
ijfw-execute
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name].
ijfw-metrics
Show IJFW token / cost / session metrics over a time window. Reads .ijfw/metrics/sessions.jsonl via the ijfwmetrics MCP tool.
release-plan
Design a pre-deploy release and rollout strategy: pick the pattern (feature flag, canary, blue-green, or progressive delivery) by risk, then specify the exposure ramp, promotion metric and threshold, and rollback trigger. Designs the rollout, never executes it. Gated --godot-mobile and --godot-desktop modes plan a…
code-locate
Locate code paths and line ranges for a described behavior: up to 10 candidates with HIGH/MEDIUM/LOW confidence and a search trail, plus a proposed SOURCEOFTRUTH.md update. Use when the first question is where one specific behavior lives and paths are unknown. Do not use when paths are explicit, the codebase is tiny…
contract-signoff
Harden the current decision set into a normative source of truth with no residual ambiguity, saved in DECISIONS.md and TASKSTATE.md as reviewable edits. Use when decisions are resolved, the contract direction is stable, and wording needs hardening before planning or implementation. Do not use when major ambiguities…