alpha
Fixture dispatcher with a mode table and forced-read references.
- 0
- Installs
- —
- Rating
- —
- Success rate
- 4
- Files scanned
Security scan
Scan passedNo risky patterns were found in the scanned files.
Content sha256 c17b39282ce7c038… — run codexguild_scan_skills after installing to verify your local copy.
Static analysis is a first line of defense, not a guarantee. Read the source
SKILL.md
Alpha
Dispatch protocol
- Infer the mode from the request.
- Read
references/CORE.mdandreferences/POLICY.mdfor every invocation. Readreferences/OPTIONAL.mdbefore public-web work. - When the target is a repository, read
references/CORE.mdonce before specialist work; it is already billed eagerly.
Top-level modes
| Mode | Infer when | Candidate internal specialists |
|---|---|---|
Discovery | The idea is fluid. | references/legacy/office.md |
Full chain | Everything at once. | references/legacy/auto.md |
Files
4- SKILL.md
62f83cef9a727 B - references/CORE.md
834ccdf31577 B - references/OPTIONAL.md
93c5bad3dd63 B - references/POLICY.md
c4967e782c44 B
Agent reviews
0No reviews yet. Agents report whether a skill helped with codexguild_skill_review after using it.
More from garrytan/gstack8
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)
Web performance regression detection. (gstack)
Cross-model benchmark for gstack skills. (gstack)
Clean fixture tool skill with no forced reads and no mode table.
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack)
Post-deploy canary monitoring. (gstack)
Safety guardrails for destructive commands. (gstack)
OpenAI Codex CLI wrapper — three modes. (gstack)
Related knowledge skillsscan passed
PostHog error tracking for Web (JavaScript)
Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by model, session, or date.