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 dppdppd/rpm --skill init-rpmgit clone --depth 1 https://github.com/dppdppd/rpmWrote 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/dppdppd/rpm/init-rpm)<a href="https://agentmods.dev/skills/dppdppd/rpm/init-rpm"><img src="https://agentmods.dev/badge/skills/dppdppd/rpm/init-rpm.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 | $0.00048 | $0.05793 |
| Opus 5 | $0.00024 | $0.02897 |
| Sonnet 5 | $0.00010 | $0.01159 |
| Haiku 4.5 | $0.00005 | $0.00579 |
Grade A, and why
init-rpm 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 8d 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 — 647 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/init-rpm — Full Instructions
Project setup and verification. First run creates rpm context for a project. Repeat runs verify that an existing rpm setup matches the latest expected layout and apply safe migrations.
Run once per project, or run again after installing rpm in a new agent
runtime such as Codex. On repeat runs, do not re-ask first-run
project context questions unless a required canonical file is missing
and the answer cannot be inferred from existing files.
If docs/rpm/context.md already exists, read it and augment — do not
overwrite. Merge in missing sections only.
If any docs/rpm/ content already exists, treat this as an rpm migration/update,
not a brand-new install. Preserve existing rpm files, create only missing
canonical files (context.md, past/log.md, present/status.md,
future/tasks.org, future/done.org, reviews/), and migrate legacy names
when present:
docs/rpm/FUTURE.orgordocs/rpm/future/FUTURE.org->docs/rpm/future/tasks.orgdocs/rpm/PRESENT.mdordocs/rpm/present/PRESENT.md->docs/rpm/present/status.mddocs/rpm/RPM-LOG.mdordocs/rpm/past/RPM-LOG.md->docs/rpm/past/log.mddocs/rpm/RPM.md->docs/rpm/context.md
Narrate as you go. At each phase, tell the user what's about to happen
in one short sentence before doing it — users should never be surprised
by what /init-rpm creates or writes.
Phase 0: Introduce
Before running anything, detect whether this is a first run:
- If
docs/rpm/does not exist, use the first-run introduction below. - If any
docs/rpm/content exists, this is a repeat run. Use the verification introduction below, then follow Repeat-run verification mode.
First-run wording (adapt freely):
## /init-rpm — rpm first-run setup
I'll set up rpm (Relentless Project Manager) for this project. Here's
what I'm about to do:
1. Detect the project — language, tests, existing docs
2. Ask 1–3 questions I can't answer from the codebase
3. Create `docs/rpm/` scaffolding (context, trackers, past/future/reviews)
4. Create an agent instructions file if one is missing
5. Ask once for runtime permissions if the active agent supports them
6. Summarize what was created
Starting with detection.
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.
- 8d ago First seen · 647 lines · 48 tokens per session scan A c2c51fd48fd3
init-rpm is a skill published in the GitHub repository dppdppd/rpm (3 stars, last pushed 9d ago), licensed MIT. It adds 48 tokens to every session and 5,793 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
docs-keeper
Maintains the four living documents of a hi-vibe project: CLAUDE.md (lean project context — constraints, pitfalls, rationale), per-folder MODULE.md (detailed design), handover.md (session-to-session context log), CHANGELOG.md (substantive change history, Keep a Changelog). Use for /hi-vibe:init, :handover, :log…
backlog
Use when the user asks to "review backlog", "analyze backlog quality", "backlog health", or invokes /compass-rose:backlog. Reads all open and wontfix issue files and analyzes quality via the backlog-analyzer agent.
reprioritize
Use when the user asks to "reprioritize", "update priorities", "scan codebase for relevance", or invokes /compass-rose:reprioritize. Scans codebase against local issue files and updates their priority/status meta tags.
add-item
Use when the user says "file an issue", "log this", "track this", "add a bug", "create a task", "add to backlog", or invokes /compass-rose:add-item. Replaces /lore-development:file-issue. Creates a local issue file in .lore/work/issues/.
roadmap
Generates ROADMAP.md from project milestones, issues, and boards (GitHub, GitLab, or Bitbucket). Structures content with mission statement, current milestone progress, upcoming milestones, and community involvement section. Use when creating or updating a project roadmap.
recursive-spine-digest
Use when sweeping all recursive-spine-conforming repos for tracking health — aging deferrals (oldest first), stalled milestones, in-flight by lane, assigned-but-untouched issues, and debts named in closing comments but never filed, plus seedling pollen that never transplanted (hive repos). Reports honest denominators…