Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/alfredoperez/speckit-companionnpx agentmods add commands/alfredoperez/speckit-companion/speckit.companion.living-showWrote 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/alfredoperez/speckit-companion/speckit.companion.living-show)<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/speckit.companion.living-show"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/speckit.companion.living-show/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/alfredoperez/speckit-companion/speckit.companion.living-show"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/speckit.companion.living-show.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 | $0.00037 | $0.00628 |
| Opus 5 | $0.00018 | $0.00314 |
| Sonnet 5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
speckit.companion.living-show 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 5d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Show
Print part of a living spec instead of opening it. A capability's spec runs to hundreds of lines, and almost every question about one is about a single requirement: what does it say, what are its scenarios, which rules describe this file I am editing. This is the terminal twin of the load steps' selective read — same parser, same counts, no viewer required.
Read-only — it never edits anything, and it never fails (always exits success). Every unanswerable question is an answer: an unregistered capability, a missing spec file, a name that matches nothing, a file nothing claims.
This is opt-in. With living specs disabled (or no config), it reports nothing and exits clean.
Prerequisites
- Verify Python is available by running
python3 --version. - If
python3is not available, warn the user and skip:[companion] Warning: python3 not detected; skipped the living spec slice.
Execution
Run one of these from the repository root, whichever the request asks for:
# every requirement heading in one capability
python3 .specify/extensions/companion/scripts/resolve-spec-paths.py --headings <capability>
# one requirement in full, including its scenarios
python3 .specify/extensions/companion/scripts/resolve-spec-paths.py --requirement "<heading>"
# the requirements that describe one source file
python3 .specify/extensions/companion/scripts/resolve-spec-paths.py --file <path>
Add --capability <name> to --requirement to search one capability instead of all of them. Add --json when a caller needs the object rather than the list.
What each mode answers
| Mode | Answers |
|---|---|
--headings |
What rules does this capability state? One heading per line, in file order, with the count. |
--requirement |
What does this one rule say, and how would anyone know it held? The heading, the normative prose, and the scenarios. |
--file |
Which durable rules describe this file? Grouped by capability, most-specific capability first. |
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.
- 5d ago First seen · 51 lines · 37 tokens per session scan A b3091651cd15
speckit.companion.living-show is a command published in the GitHub repository alfredoperez/speckit-companion (90 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 628 once invoked, about $0.0002 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 2026-09-07.
Other commands, from other repositories
migrate-to-typescript
Migrate JavaScript project to TypeScript.
svelte:component
Create new Svelte components with best practices, proper structure, and optional TypeScript support.
autospec.plan
Generate YAML implementation plan from feature specification.
code-locate
Given a behavior description, locate candidate code paths and line ranges in the active codebase that probably implement it. Output up to 10 candidates with HIGH/MEDIUM/LOW confidence, one-line rationale per candidate, and an explicit search trail; propose a SOURCEOFTRUTH.md update so the next workflow step (typically…
harvest-session-learnings
Scan the current working session and the active task's artifacts for reusable, generalizable lessons (what was tried, what failed and why, what surprised us, what the next task should do differently) and propose anchored entries to append to the task's LEARNINGS.md, the produce-side counterpart to the ADR-0017 consume…
screen-spec
Generate a screen specification from a Figma frame using MCP tools (getdesigncontext, getscreenshot). Produces a spec doc matching the SCREENSPEC.md template with layout sketch, components used, spacing observed, data dependencies, copy, accessibility notes, interactions, and error states. Use when documenting a…