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/speckit.bug.test)<a href="https://agentmods.dev/commands/loulanyue/spec-kit-zh/speckit.bug.test"><img src="https://agentmods.dev/badge/commands/loulanyue/spec-kit-zh/speckit.bug.test/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/speckit.bug.test"><img src="https://agentmods.dev/badge/commands/loulanyue/spec-kit-zh/speckit.bug.test.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 | $0.00013 | $0.01381 |
| Opus 5.5 | $0.00005 | $0.00552 |
| Sonnet 5.5 | $0.00003 | $0.00276 |
| Haiku 4.5 | $0.00001 | $0.00138 |
Grade A, and why
speckit.bug.test 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 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.
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.
This is a copy
100% identical to speckit.bug.test — 84 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Bug Fix
Validate that the fix recorded by __SPECKIT_COMMAND_BUG_FIX__ actually resolves the bug described by __SPECKIT_COMMAND_BUG_ASSESS__. The output is a verification report at .specify/bugs/<slug>/test.md.
User Input
$ARGUMENTS
The user input should identify the bug to validate. Accept any of:
slug=<bug-slug>or--slug <bug-slug>or a bare slug-like token.- A path that contains the slug (e.g.
.specify/bugs/login-timeout/). - Nothing — fall back to context (see below).
Slug Resolution
Resolve BUG_SLUG in this order, stopping at the first match:
- Explicit user input — a slug passed in
$ARGUMENTS(any of the forms above). - Conversation context — if the current session has just run
__SPECKIT_COMMAND_BUG_ASSESS__or__SPECKIT_COMMAND_BUG_FIX__, the slug it reported is the working slug. Reuse it without re-prompting. Confirm it by checking that.specify/bugs/<slug>/fix.mdexists; if it does not, fall through. - Single candidate on disk — list
.specify/bugs/*/fix.md. If exactly one bug has afix.md, use it. - Disambiguate:
- Interactive mode: ask the user which bug to validate and list the candidates.
- Automated mode: stop with an error listing the candidates. Do not guess.
Once resolved, set BUG_SLUG and BUG_DIR = .specify/bugs/<BUG_SLUG>, and briefly state in your reply which resolution path was used (explicit / from context / single candidate / asked).
Prerequisites
BUG_DIR/assessment.mdMUST exist.BUG_DIR/fix.mdMUST exist. If not, stop and instruct the user to run__SPECKIT_COMMAND_BUG_FIX__first.- If
BUG_DIR/test.mdalready exists, ask the user whether to overwrite it (interactive mode) or refuse (automated mode). - Read both
assessment.mdandfix.mdin full so you know:- The original symptom and reproduction steps (from
assessment.md). - The actual code changes and tests added (from
fix.md).
- The original symptom and reproduction steps (from
Execution
- Plan the validation
- Decide which checks prove the bug is gone:
- Re-run the reproduction steps from the assessment (or their automated equivalent).
- Run the tests added or updated in the fix.
- Run any broader regression suite that touches the changed files.
- Decide which checks prove nothing was broken:
- Existing test suites for the changed modules.
- Lint / type-check if the project uses them.
- Decide which checks prove the bug is gone:
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 · 118 lines · 13 tokens per session scan A ac2ab5542b0a
speckit.bug.test is a command published in the GitHub repository loulanyue/spec-kit-zh (337 stars, last pushed 13d ago), licensed MIT. It adds 13 tokens to every session and 1,381 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to speckit.bug.test, differing in 84 lines, and is treated as a copy.
Other commands, from other repositories
validate-build
Validates project build process. Run after changes to ensure the project compiles/transpiles correctly.
meta-theory-verify
Run the appropriate MetaKim verification path.
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.
doctor
Run IJFW health check (files, MCP server, hooks, memory, caps, framing).
ai-feature-eval-harness
Design an eval plan for a product AI feature: success criteria, a held-out labeled dataset, per-criterion grading (code-based, then LLM-based), and a pass threshold. Use when a task ships or changes a feature with non-deterministic model output (classification, extraction, summarization, ranking, agent action) needing…