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 danielrosehill/Claude-SOP-Writer-Plugin --skill bump-revisiongit clone --depth 1 https://github.com/danielrosehill/Claude-SOP-Writer-PluginWrote 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/danielrosehill/claude-sop-writer-plugin/bump-revision)<a href="https://agentmods.dev/skills/danielrosehill/claude-sop-writer-plugin/bump-revision"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-sop-writer-plugin/bump-revision/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/danielrosehill/claude-sop-writer-plugin/bump-revision"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-sop-writer-plugin/bump-revision.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00093 | $0.00647 |
| Opus 5.5 | $0.00037 | $0.00259 |
| Sonnet 5.5 | $0.00019 | $0.00129 |
| Haiku 4.5 | $0.00009 | $0.00065 |
Grade A, and why
bump-revision 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 2mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bump-revision
Bump revision metadata across one or more SOPs.
Inputs to gather
- Targets — one of:
- A specific file path
- A glob (
sops/*.typ) - A binder name from
binders.yaml(bumps every doc in that binder) all— every.typSOP in the project (confirm before doing this)
- Bump level —
patch(default — 1.0 → 1.0.1),minor(1.0 → 1.1), ormajor(1.0 → 2.0). - Note (optional) — a short revision-note string to append to the doc's revision history block.
- Recompile? (default yes) — after bumping, run
compileon each affected doc and rebuild any binder that references it.
What to do
- Resolve targets to a concrete file list. Confirm with the user if
allwas requested or the list is large (>10 files). - For each file:
- Parse the leading metadata. Plugin convention is a Typst block at the top:
#let meta = ( title: "Rocket & Missile Alert Response", revision: "1.2", date: "2026-04-01", audience: "household members", source: "Home Front Command", ) - Bump
revisionper the requested level. - Set
dateto today's ISO date. - If a
revisions:history list exists, append(version: "<new>", date: "<today>", note: "<note>"). - Write back.
- Parse the leading metadata. Plugin convention is a Typst block at the top:
- If recompile: invoke
compilefor each updated.typ. If any of them belong to a binder defined inbinders.yaml, also rebuild that binder. - Print a summary: which files were bumped (old → new version), and which PDFs were regenerated.
Notes
- Be conservative parsing the metadata block — if a doc doesn't follow the convention, skip it and report it; don't try to invent metadata.
- The metadata convention is plugin-recommended, not required. Documents without it are still valid SOPs; they just opt out of
bump-revision. - Revision strings are free-form in the source — common patterns:
"1.0","2024.04","r3". Prefer semver-ish but accept whatever's already there and increment numerically where possible. If unparseable, ask.
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.
- 2mo ago First seen · 47 lines · 0 tokens per session scan A 7fa4b47124e9
bump-revision is a skill published in the GitHub repository danielrosehill/Claude-SOP-Writer-Plugin (3 stars, last pushed 6mo ago), licensed MIT. It adds 93 tokens to every session and 647 once invoked, about $0.0004 per session on Opus 5.5. 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.
bump-revision compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bump-revisiondanielrosehill/Claude-SOP-Writer-Plugin | Skill | 3 | 6mo ago | MIT | A | 93 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 3d ago | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| ppt-reviewOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 2 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |