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-syncWrote 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-sync)<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/speckit.companion.living-sync"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/speckit.companion.living-sync/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-sync"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/speckit.companion.living-sync.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 | $0.00041 | $0.01643 |
| Opus 5.5 | $0.00016 | $0.00657 |
| Sonnet 5.5 | $0.00008 | $0.00329 |
| Haiku 4.5 | $0.00004 | $0.00164 |
Grade A, and why
speckit.companion.living-sync 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 1mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Living Specs
Bring every affected living spec up to date with the code as it is right now — uncommitted edits, deletions, and untracked files included — in a single pass. This is the one-command loop for a developer who codes directly, without running the Companion pipeline: no drift report to read, no capability to hand-pick, no blind spot for work that isn't committed yet. The updated spec files are left as ordinary working-tree edits so they commit together with the code that caused them.
This is opt-in. With living specs disabled (or no config), it reports nothing to do and exits clean. It never fails the host run: any miss degrades into a warning and a skip.
Prerequisites
- Verify Python is available by running
python3 --version. - If
python3is not available, warn the user and stop here without failing:[companion] Warning: python3 not detected; skipped living-spec sync.
The smallest thing that works
Before building anything, stop at the first rung that holds: does it need to exist at all; does this codebase already have it; does the standard library, the platform, or an installed dependency do it; can it be one line; only then, the minimum code that works. Fix the cause where every caller passes through, not the symptom one caller reported. Delete rather than add, boring rather than clever: no interface with one implementation, no factory for one product, no scaffolding for later. Lean governs what you build and write, not how the work is split: sending work to a worker where a step says to is not extra.
Write it the way you would say it. One idea per sentence. No em-dashes: a full stop, a comma or a colon says it. Say what happens, not what the system "shall be capable of". Never a section that exists to say "N/A": remove it instead.
The same test governs what you write, and again once it is written. A section nobody acts on is removed, not filled in. No requirement for what a type or a test already enforces. A third scenario has to cover a failure the first two miss. Then reread and cut: the sentence restating the one before it, the example longer than its rule, the clause defending a choice nobody challenged, the prose repeating a table. Each reads as thoroughness and is what makes a body too long to follow.
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.
- 1mo ago Changed ad6618644796
- 1mo ago Changed 4f8d903f2a1f
- 1mo ago Changed e56e978b24a7
- 1mo ago Changed · +14 lines a8a084cf9661
- 1mo ago Changed · +9 lines bfa18c99a9b6
- 1mo ago First seen · 59 lines · 41 tokens per session scan A 893a8ce97178
speckit.companion.living-sync is a command published in the GitHub repository alfredoperez/speckit-companion (99 stars, last pushed 9d ago), licensed MIT. It adds 41 tokens to every session and 1,643 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
commit
When you receive this command, do the following.
pre-commit-check
Tu es un assistant de qualité code. Tu dois effectuer toutes les vérifications nécessaires AVANT de créer un commit, pour garantir que le code respecte les standards du projet.
commit
Stage and commit with a conventional-commit message the auto-release bot can read.
pre-commit-audit
Deliver a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode carriers. Use when the user requests a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode…
branch-commit
Return a branch name and concise commit message (max 3 lines) for the current task, grounded in the real git diff; with --apply, create the commit after showing the staged diff. Use when the user only needs quick branch and commit naming before committing, PR packaging is unnecessary, and a real diff exists; use…
approve-proposed
Atomically persist every file marked PROPOSED in the most recent prior assistant turn's ### Artifact changes block, promoting staged content to real files. Invoked on request only. Use when that block contained files marked PROPOSED and you have accepted the inline content of each. Do not use when the prior turn had…