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/arrrrny/zuraffaWrote 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/arrrrny/zuraffa/speckit.gh-triage.feature)<a href="https://agentmods.dev/commands/arrrrny/zuraffa/speckit.gh-triage.feature"><img src="https://agentmods.dev/badge/commands/arrrrny/zuraffa/speckit.gh-triage.feature/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/arrrrny/zuraffa/speckit.gh-triage.feature"><img src="https://agentmods.dev/badge/commands/arrrrny/zuraffa/speckit.gh-triage.feature.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 | $0.00033 | $0.01507 |
| Opus 5 | $0.00016 | $0.00754 |
| Sonnet 5 | $0.00007 | $0.00301 |
| Haiku 4.5 | $0.00003 | $0.00151 |
Grade A, and why
speckit.gh-triage.feature 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 7d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Triage — Create Feature Issue
File a new GitHub issue that describes a feature request, label it with the
configured feature label (e.g. enhancement), and — when configured or asked —
turn it into a spec by running __SPECKIT_COMMAND_SPECIFY__ automatically.
By default this command only creates the issue. The spec workflow runs
automatically when the config key auto_specify is true, or when you pass the
--specify flag for a single run; otherwise only the issue is filed.
User Input
$ARGUMENTS
Accept any of:
--title "<title>"— the feature title. If omitted, the first line of the input becomes the title.--body "<body>"— the feature description. If omitted, the remaining input (after the title line) becomes the body; if there is no remaining input, the title is reused.--repo <owner>/<repo>— where to file the issue (elserepo:from config, else the current git remote).--specify— after the issue is created, automatically run__SPECKIT_COMMAND_SPECIFY__to create a spec from it. This forces the spec step on for this run even ifauto_specifyisfalsein config.- A bare description (no flags) is treated as the feature request text.
Whether the spec is created automatically is decided by --specify OR config:
read .specify/extensions/gh-triage/gh-triage-config.yml and use the auto_specify
key (default false). When auto_specify: true, the spec is created automatically
with no flag needed; --specify overrides and forces it on for a single run.
Prerequisites
-
The
ghCLI must be installed and authenticated (gh auth status). If it is not, stop and tell the user to rungh auth login. -
The engine script must be present:
ENGINE=".specify/extensions/gh-triage/scripts/bash/gh-triage.sh" if [ ! -x "$ENGINE" ]; then echo "gh-triage engine not found at $ENGINE — reinstall with: specify extension add --dev <path-to-gh-triage>" exit 1 fi -
The feature label is read directly from
.specify/extensions/gh-triage/gh-triage-config.yml(labels.feature, defaultenhancement). Only labels that actually exist in the target repo are applied — if the repo lacks the configured label, the engine skips it with a warning rather than force-creating it. The same config file holdsauto_specify(defaultfalse), which controls whether the spec step runs automatically.
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.
- 7d ago Changed · +2 lines a1adaf0788c8
- 10d ago First seen · 115 lines · 33 tokens per session scan A 5188740a34f2
speckit.gh-triage.feature is a command published in the GitHub repository arrrrny/zuraffa (5 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,507 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 2026-08-31.
Other commands, from other repositories
auto-sprint
Orchestrateur de sprint de bout en bout (démarrage -> décomposition -> validation -> implémentation -> PR -> CI -> revue -> rétro -> merge).
review
Préparation Sprint Review.
afcl
Close feature [agent] [--adopt] - merges branch, cleans up, optionally adopts from losers (shortcut for feature-close).
next
Suggest the most likely next workflow action based on current context.
aft
Transfer feature from its current agent to a different agent — preserves commits and in-flight work (shortcut for feature-transfer).
create-task-list-for-issue.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.