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/rhuss/cc-spexWrote 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/rhuss/cc-spex/speckit.spex.walkthrough)<a href="https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex.walkthrough"><img src="https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex.walkthrough/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/rhuss/cc-spex/speckit.spex.walkthrough"><img src="https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex.walkthrough.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 | $0.00027 | $0.04958 |
| Opus 5.5 | $0.00011 | $0.01983 |
| Sonnet 5.5 | $0.00005 | $0.00992 |
| Haiku 4.5 | $0.00003 | $0.00496 |
Grade A, and why
speckit.spex.walkthrough 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 — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Walkthrough - Try the Feature with a Runbook
Overview
The point of this command is trust through trying the feature. It writes a
tutorial-style RUNBOOK.md: one end-to-end journey a person can follow to see
the feature actually work, where every step says why it matters, the exact
command to run, and what you should see before you run it. Then it runs that
runbook with you as a co-pilot: for each step you either run the command
yourself (it lands on your clipboard) or let the agent run it with full
transparency (the exact command, the real output, and an expected-versus-actual
comparison).
If nothing can be tried by hand, this command says so in one line and writes no
files. It never fabricates output, never presents a command you cannot copy and
run, and never hard-blocks finish or ship.
Deterministic helpers (Constitution VII)
All state, freshness, structure checks, fixture lifecycle, and clipboard access
live in scripts. This command delegates to them and never re-implements their
logic inline. Resolve each from the extension's installed scripts/ directory,
falling back to the canonical repo path:
STATUS=".specify/extensions/spex/scripts/spex-runbook-status.sh"
CHECK=".specify/extensions/spex/scripts/spex-runbook-check.sh"
FIXTURE=".specify/extensions/spex/scripts/spex-runbook-fixture.sh"
CLIP=".specify/extensions/spex/scripts/spex-runbook-clip.sh"
[ -f "$STATUS" ] || STATUS="spex/scripts/spex-runbook-status.sh"
[ -f "$CHECK" ] || CHECK="spex/scripts/spex-runbook-check.sh"
[ -f "$FIXTURE" ] || FIXTURE="spex/scripts/spex-runbook-fixture.sh"
[ -f "$CLIP" ] || CLIP="spex/scripts/spex-runbook-clip.sh"
The runbook path always comes from "$STATUS" locate. Never guess it, and never
edit .gitignore or .git/info/exclude (the scratch folder ignores itself).
You MUST NOT simulate, summarize, or hand-write what the system would do. Every
step runs the real command or the real action. If a step cannot be genuinely run
by either party, record it as skipped with an honest reason, never as a pass.
Before any command output is written into the runbook, redact credentials to
[redacted] (FR-028).
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 Changed · +17 lines 42ac960190c6
- 5d ago First seen · 431 lines · 27 tokens per session scan A 44536078e1c9
speckit.spex.walkthrough is a command published in the GitHub repository rhuss/cc-spex (120 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 4,958 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-13.
Other commands, from other repositories
playwright-test-heal
Run all my tests and fix the failing ones.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
verify-pr
Verify a PR's frontend changes through browser automation.
test-run
Run E2E tests with qa-use CLI.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.