repoprompt-tool-guidance-refresh

repoprompt-tool-guidance-refresh is a skill for Claude Code from w-winter/dot314. It costs 115 tokens per session (1,738 once invoked), scanned A, original, MIT.

A maintenance guide for keeping RepoPrompt command and tool documentation current. RepoPrompt is a command-line and tool interface for giving coding agents focused views of a repository.

In plain words
What is it for?
Use it before and after upgrading RepoPrompt, or for a one-time comparison of the maintained CE command line with the frozen Classic version.
Why use it?
It helps detect changes between RepoPrompt versions or between its maintained and older command-line variants.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/track-rp-version.sh --ce --force.

Good fit Use it before and after upgrading RepoPrompt, or for a one-time comparison of the maintained CE command line with the frozen Classic version.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/w-winter/dot314
agentmods
npx agentmods add skills/w-winter/dot314/repoprompt-tool-guidance-refresh

Made for: Claude Code.

Wrote 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.

agentmods badge for repoprompt-tool-guidance-refresh

README.md
[![agentmods](https://agentmods.dev/badge/skills/w-winter/dot314/repoprompt-tool-guidance-refresh.svg)](https://agentmods.dev/skills/w-winter/dot314/repoprompt-tool-guidance-refresh)
Your own site
<a href="https://agentmods.dev/skills/w-winter/dot314/repoprompt-tool-guidance-refresh"><img src="https://agentmods.dev/badge/skills/w-winter/dot314/repoprompt-tool-guidance-refresh.svg" alt="Measured on agentmods" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,738 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 56
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00115 $0.01738
Opus 5 $0.00057 $0.00869
Sonnet 5 $0.00023 $0.00348
Haiku 4.5 $0.00012 $0.00174

Measured 9d ago against content hash 9bb41578ccbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

repoprompt-tool-guidance-refresh 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 9d 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.

skills/repoprompt-tool-guidance-refresh/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow

RepoPrompt CE (rpce-cli) is the maintained target and the default for this skill. RepoPrompt Classic (rp-cli) is frozen — it no longer changes, so you only touch it for a one-shot cross-app comparison.

Two comparison modes:

  • Same CLI across versions (the normal loop): older rpce-cli → newer rpce-cli, run as a pre/post pair around a CE upgrade.
  • Across apps (one-shot): Classic rp-cli vs CE rpce-cli, to understand where CE's tools/flags diverge from frozen Classic.

Canonical locations (use these even if your working directory differs):

  • Skill directory: ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/ (may be a symlink target)
  • Script: ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh
  • Output directory: ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/rp-tool-defs/

Snapshots are namespaced per CLI so Classic and CE never collide: CE writes rpcecli-help__{VERSION}.txt / rpcecli-l__{VERSION}.txt with baseline .baseline_version__rpcecli; Classic writes rpcli-* (frozen, last captured at v2.1.29).

Phase A — Pre-Upgrade (invoke BEFORE updating RepoPrompt CE)

  1. Run the version tracking script:

    ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh --pre
    

    (Defaults to CE. Equivalent if you cd into the skill dir: ./scripts/track-rp-version.sh --pre.)

  2. The script writes a baseline snapshot under rp-tool-defs/:

    • .baseline_version__rpcecli — the baseline rpce-cli version
    • rpcecli-help__{VERSION}.txt — output of rpce-cli --help
    • rpcecli-l__{VERSION}.txt — output of rpce-cli -l
  3. Stop here. Tell the user:

    ✓ Baseline captured at v{VERSION}. Go update RepoPrompt CE, then re-invoke this skill.

Phase B — Post-Upgrade (invoke AFTER updating RepoPrompt CE)

  1. Run the version tracking script:
    ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh --post
    

Read the full file on GitHub · 129 lines

Files

What ships with it

60 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.

Changes

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.

  1. 9d ago First seen · 129 lines · 115 tokens per session scan A 9bb41578ccbe

Subscribe to this mod's changes

repoprompt-tool-guidance-refresh is a skill published in the GitHub repository w-winter/dot314 (130 stars, last pushed 3d ago), licensed MIT. It adds 115 tokens to every session and 1,738 once invoked, about $0.0006 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.