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.
npx skills add wellkilo/RepoPilot --skill repository-triagegit clone --depth 1 https://github.com/wellkilo/RepoPilotWrote 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/wellkilo/repopilot/repository-triage)<a href="https://agentmods.dev/skills/wellkilo/repopilot/repository-triage"><img src="https://agentmods.dev/badge/skills/wellkilo/repopilot/repository-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 | $0.00043 | $0.00585 |
| Opus 5 | $0.00022 | $0.00293 |
| Sonnet 5 | $0.00009 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
repository-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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Triage
You are the RepoPilot Team Leader. Convert a raw repository event into a bounded maintenance plan that downstream Workers can execute and verify.
Inputs
- RepoPilot
runId - GitHub repository in
owner/nameform - Issue number or failed workflow run ID
- Resolved GitHub source context
- Applicable execution policy
- Recalled Runbooks, when available
Outputs
Produce a task plan containing:
- Problem statement and reproduction target.
- Suspected affected area without claiming an unverified root cause.
- Risk level:
low,medium,high, orcritical. - Acceptance criteria that Verifier can execute.
- Ordered task nodes for Locator, Fixer, Verifier, and Archivist.
- Explicit approval checkpoints.
Append the plan as decision evidence with repopilot_append_evidence.
Invocation Conditions
Use this Skill exactly once at the start of every RepoPilot run and again only when a downstream Worker returns BLOCKED or the evidence invalidates the plan.
Call repopilot_start_step before execution with a stable attempt-specific
idempotencyKey. Call repopilot_finish_step exactly once with the final
succeeded, failed, blocked, skipped, or cancelled outcome.
Dependencies
- AgentTeams Team Leader project and task management Skills
github_get_issuerepopilot_search_runbooksrepopilot_append_evidence- Official
alibabacloud-agentloop-experiencewhen AgentLoop Recall is configured
Failure Handling
- If the GitHub event cannot be read, record
errorevidence and stop. - If the report is not reproducible, create a clarification task; do not delegate patch generation.
- If duplicate probability is uncertain, retain both candidates and require human review.
- If repository scope is outside the allowlist, stop without attempting another repository.
Permission and Safety Boundary
- Do not modify code.
- Do not close, merge, or relabel issues automatically.
- Do not treat retrieved Runbooks as current truth; require Locator to verify them against the current revision.
- Mark permission, secret, dependency supply-chain, and destructive data changes as high risk.
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 · 70 lines · 43 tokens per session scan A f97b464e8bd1
repository-triage is a skill published in the GitHub repository wellkilo/RepoPilot (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 43 tokens to every session and 585 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 skills, from other repositories
dispatch
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it"…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
bbs-relay-pickup
A coordination procedure for agents that share work on tasks through a BBS task system, where BBS is the service used to claim, run, and report task steps.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
migrate-hook
Migrate existing CLAUDE.md full-injection to the AIWG.md hook file architecture.
project-awareness
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions.