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/Data-Wise/craftnpx agentmods add skills/data-wise/craft/repo-triageWrote 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/skills/data-wise/craft/repo-triage)<a href="https://agentmods.dev/skills/data-wise/craft/repo-triage"><img src="https://agentmods.dev/badge/skills/data-wise/craft/repo-triage.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.02184 |
| Opus 5 | $0.00042 | $0.01092 |
| Sonnet 5 | $0.00017 | $0.00437 |
| Haiku 4.5 | $0.00008 | $0.00218 |
Grade A, and why
repo-triage 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 6d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Triage Skill
Batch-grounds open GitHub issues and stale worktrees/branches against current repo state, offers confirmed deletion/closure of what's superseded, and groups everything else into grill-ready / plan-ready / defer buckets. A thin orchestrator over three existing pieces — it contributes no parallel classification or merge-detection logic of its own beyond the join/bucket step (Phase 3/4).
Boundary with Adjacent Skills
| Skill / Operation | Owns | repo-triage's relationship |
|---|---|---|
commands/git/issue-check.md (classify_issue()) |
Single-issue premise verdict (valid/moot/unclear) | Runtime-extracted and reused verbatim via utils/repo_triage_classify.py — never reimplemented. See "Source identity" below. |
dev/git Operation 4 (Branch Cleanup) |
Detecting locally-merged/squash-merged branches | Called via branch_cleanup_dry_run() (lib/git-utils.sh) — collection only, no deletion. |
dev/git Operation 5 (Worktree Management, clean) |
Detecting stale/merged worktrees | Called via worktree_clean_dry_run() (lib/git-utils.sh) — collection only, no removal. |
skills/workflow/grill/SKILL.md |
Interrogating a genuinely unresolved, load-bearing design question | repo-triage's grill-ready bucket reuses grill's own self-definition ("load-bearing branch") as the membership test — never a separate taxonomy. |
This skill never deletes a branch, removes a worktree, or closes an issue on its own initiative — every mutation requires an explicit confirm captured in the same run (see Confirm UX below).
Procedure
Step 1 — Issue triage (no pre-filter, no concurrency cap)
python3 utils/repo_triage_classify.py Data-Wise/craft
This loops over every open issue from gh issue list, classifying each with
the SAME classify_issue() that commands/git/issue-check.md and
tests/test_issue_check_unit.py use — extracted at runtime from that file's
fenced ```python block, never copied. tests/test_repo_triage_classify_unit.py
asserts source identity between the two loaders as a standing regression
guard: if repo-triage ever grows a parallel classifier, that test fails.
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.
- 6d ago First seen · 169 lines · 84 tokens per session scan A 9e2f037b26c2
repo-triage is a skill published in the GitHub repository Data-Wise/craft (4 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 2,184 once invoked, about $0.0004 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 skills, from other repositories
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
auto
Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…
agent-orchestration
Agent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows. Use when building autonomous agent loops, coordinating multiple agents, evaluating CrewAI/AutoGen/Swarm, or orchestrating complex multi-step scenarios.
architecture-decision-record
ADR templates in the Nygard format with context, decision, consequences, and alternatives. Use when writing ADRs, recording an architectural decision, or evaluating options.
code-review
Orchestrates code review by detecting the project language and architecture, then routing to the appropriate specialized review skill (code-review-go, code-review-typescript, code-review-python, code-review-php, code-review-architecture). Falls back to the generic checklist when no specific skill applies. Invoked when…
new-gh-issue-orchestration
Orchestrates a GitHub-issue-driven delivery workflow from issue intake to PR creation using reviewer-first then worker execution. Invoked when the user provides a GitHub issue link/number and asks to start end-to-end delivery.