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/w-winter/dot314npx agentmods add skills/w-winter/dot314/repoprompt-tool-guidance-refreshWrote 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/w-winter/dot314/repoprompt-tool-guidance-refresh)<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>- NVIDIA SkillSpector warn
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.
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 | $0.00115 | $0.01738 |
| Opus 5 | $0.00057 | $0.00869 |
| Sonnet 5 | $0.00023 | $0.00348 |
| Haiku 4.5 | $0.00012 | $0.00174 |
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.
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→ newerrpce-cli, run as a pre/post pair around a CE upgrade. - Across apps (one-shot): Classic
rp-clivs CErpce-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)
-
Run the version tracking script:
~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh --pre(Defaults to CE. Equivalent if you
cdinto the skill dir:./scripts/track-rp-version.sh --pre.) -
The script writes a baseline snapshot under
rp-tool-defs/:.baseline_version__rpcecli— the baselinerpce-cliversionrpcecli-help__{VERSION}.txt— output ofrpce-cli --helprpcecli-l__{VERSION}.txt— output ofrpce-cli -l
-
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)
- Run the version tracking script:
~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh --post
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.
- references/changelog-latest.md 1.5 KB
- rp-cli-prompts/rp-address-review-cli.md 1.6 KB
- rp-cli-prompts/rp-review-chat-cli.md 3.0 KB
- rp-tool-defs/rpcecli-help__1.0.21.txt 16 KB
- rp-tool-defs/rpcecli-help__1.0.22.diff 0 B
- rp-tool-defs/rpcecli-help__1.0.22.txt 16 KB
- rp-tool-defs/rpcecli-l__1.0.21.txt 54 KB
- rp-tool-defs/rpcecli-l__1.0.22.diff 0 B
- rp-tool-defs/rpcecli-l__1.0.22.txt 54 KB
- rp-tool-defs/rpcli-help__1.5.68.txt 9.0 KB
- rp-tool-defs/rpcli-help__1.6.0.diff 1.3 KB
- rp-tool-defs/rpcli-help__1.6.0.txt 9.0 KB
- rp-tool-defs/rpcli-help__1.6.1.diff 796 B
- rp-tool-defs/rpcli-help__1.6.1.txt 9.1 KB
- rp-tool-defs/rpcli-help__1.6.10.diff 0 B
- rp-tool-defs/rpcli-help__1.6.10.txt 9.1 KB
- rp-tool-defs/rpcli-help__1.6.11.diff 0 B
- rp-tool-defs/rpcli-help__1.6.11.txt 9.1 KB
- rp-tool-defs/rpcli-help__1.6.12.diff 0 B
- rp-tool-defs/rpcli-help__1.6.12.txt 9.1 KB
- rp-tool-defs/rpcli-help__1.6.13.diff 0 B
- rp-tool-defs/rpcli-help__1.6.13.txt 9.1 KB
- rp-tool-defs/rpcli-help__1.6.14.diff 1.5 KB
- rp-tool-defs/rpcli-help__1.6.14.txt 10 KB
- rp-tool-defs/rpcli-help__1.6.4.diff 0 B
- rp-tool-defs/rpcli-help__1.6.4.txt 9.1 KB
- rp-tool-defs/rpcli-help__1.6.8.txt 9.1 KB
- rp-tool-defs/rpcli-help__1.6.9.diff 0 B
- rp-tool-defs/rpcli-help__1.6.9.txt 9.1 KB
- rp-tool-defs/rpcli-help__2.0.1.diff 0 B
- rp-tool-defs/rpcli-help__2.0.1.txt 10 KB
- rp-tool-defs/rpcli-help__2.0.12.diff 0 B
- rp-tool-defs/rpcli-help__2.0.12.txt 10 KB
- rp-tool-defs/rpcli-help__2.0.14.diff 0 B
- rp-tool-defs/rpcli-help__2.0.14.txt 10 KB
- rp-tool-defs/rpcli-help__2.0.2.txt 10 KB
- rp-tool-defs/rpcli-help__2.0.20.diff 0 B
- rp-tool-defs/rpcli-help__2.0.20.txt 10 KB
- rp-tool-defs/rpcli-help__2.0.5.diff 0 B
- rp-tool-defs/rpcli-help__2.0.5.txt 10 KB
- rp-tool-defs/rpcli-help__2.0.9.diff 0 B
- rp-tool-defs/rpcli-help__2.0.9.txt 10 KB
- rp-tool-defs/rpcli-help__2.1.1.diff 7.0 KB
- rp-tool-defs/rpcli-help__2.1.1.txt 12 KB
- rp-tool-defs/rpcli-help__2.1.11.diff 0 B
- rp-tool-defs/rpcli-help__2.1.11.txt 14 KB
- rp-tool-defs/rpcli-help__2.1.13.diff 0 B
- rp-tool-defs/rpcli-help__2.1.13.txt 14 KB
- rp-tool-defs/rpcli-help__2.1.14.diff 1.2 KB
- rp-tool-defs/rpcli-help__2.1.14.txt 15 KB
- rp-tool-defs/rpcli-help__2.1.16.diff 0 B
- rp-tool-defs/rpcli-help__2.1.16.txt 15 KB
- rp-tool-defs/rpcli-help__2.1.20.diff 0 B
- rp-tool-defs/rpcli-help__2.1.20.txt 15 KB
- rp-tool-defs/rpcli-help__2.1.29.diff 1.3 KB
- rp-tool-defs/rpcli-help__2.1.29.txt 15 KB
- rp-tool-defs/rpcli-help__2.1.3.diff 100 B
- rp-tool-defs/rpcli-help__2.1.3.txt 12 KB
- rp-tool-defs/rpcli-help__2.1.4.diff 635 B
- rp-tool-defs/rpcli-help__2.1.4.txt 13 KB
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.
- 9d ago First seen · 129 lines · 115 tokens per session scan A 9bb41578ccbe
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.
Other skills, from other repositories
harness-ci
Load to wire, tune, or debug a repo's harness-only skip.
<skill-name>
Load to .
my-skill
When to load this skill. Agents read this line to decide whether to load it, so be specific.
write-swift
How to write modern Swift well — modeling with value types, Swift 6 data-race safety and approachable concurrency (@concurrent, main-actor-by-default, actors, task groups), protocols and generics (some vs any), API design, performance and ARC, Swift Testing, macros, and the modern language features agents don't know…
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…