Borrowing it
Nothing to install: this file belongs to repoprompt/repoprompt-ce. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/repoprompt/repoprompt-ce/main/.agents/skills/rpce-maintainer-guidance/SKILL.mdgit clone --depth 1 https://github.com/repoprompt/repoprompt-ceWrote 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/repoprompt/repoprompt-ce/rpce-maintainer-guidance)<a href="https://agentmods.dev/skills/repoprompt/repoprompt-ce/rpce-maintainer-guidance"><img src="https://agentmods.dev/badge/skills/repoprompt/repoprompt-ce/rpce-maintainer-guidance/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/skills/repoprompt/repoprompt-ce/rpce-maintainer-guidance"><img src="https://agentmods.dev/badge/skills/repoprompt/repoprompt-ce/rpce-maintainer-guidance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.01418 |
| Opus 5 | $0.00044 | $0.00709 |
| Sonnet 5 | $0.00017 | $0.00284 |
| Haiku 4.5 | $0.00009 | $0.00142 |
Grade A, and why
rpce-maintainer-guidance 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 11d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RepoPrompt CE Maintainer Guidance
Use this skill as a project decision guide, not as an imitation of a person. Do not attribute inferred opinions to any individual. State uncertainty, cite the relevant principle, and let current repository instructions, source code, tests, product behavior, and explicit maintainer decisions override historical guidance.
Read references/guidance-sources.md when the task needs the evidence behind a principle, involves a disputed tradeoff, or changes model defaults, telemetry, Agent Mode, MCP, worktrees, persistence, or release behavior.
Decision workflow
- Define the observable user impact and the invariant that should hold.
- Trace the real execution path and source of truth before proposing a fix.
- Separate confirmed facts, plausible mechanisms, unproven hypotheses, and unknowns.
- Split mixed failure modes into independently testable issues or PR tracks.
- Choose the smallest coherent change that fixes the cause without creating a parallel authority or speculative compatibility layer.
- Check user-state, migration, crash, restart, cancellation, and partial-success behavior before declaring the design safe.
- Check scale and concurrency: project-size growth, CPU contention, off-main-actor synchronization, caching, coalescing, and accidental whole-root work.
- Keep asynchronous work observable. If users or agents cannot tell what is running, add an appropriate status or tool-card surface.
- Validate at the affected boundary with the smallest useful test, then exercise the real UI or live MCP path when behavior depends on integration.
- Recommend one of: implement now, investigate first, file or update an issue, stage as a follow-up, or decline as unnecessary.
Core principles
Fix causes, not symptoms
- Ask why the unexpected state, stall, timeout, or invalid value exists.
- Reject patches that merely mask a stall, retry around unexplained state, or replace data with blanks.
- Treat extra fallbacks as complexity that must earn its place with a demonstrated failure mode.
- Prefer an investigation when the causal chain is not yet supported by evidence.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 103 lines · 87 tokens per session scan A b7e5b1ef30a3
rpce-maintainer-guidance is a skill published in the GitHub repository repoprompt/repoprompt-ce (927 stars, last pushed today), licensed Apache-2.0. It adds 87 tokens to every session and 1,418 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 2026-08-30.
Other skills, from other repositories
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
architecture
Use when reviewing architecture in any codebase — module boundaries, stated design contracts, abstraction depth, error-handling design. Assess by default, apply changes on request; complexity is dependencies plus obscurity, and deep modules win.
genie-orca-review
Independent, read-only review of a group, a wish, or a PR on Orca — SHIP / FIX-FIRST / BLOCKED with severity-tagged findings. Council and retro are this skill with a different input.
remarc
Manage Remarc session comments and contextual feedback. Use when the user mentions Remarc sessions, comments, handoff, triage, review, addressing, resolving, status updates, or summaries.
pr-review
Intent-aware map-reduce PR review with CI/CD support, confidence gating, and intelligent comment deduplication.