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 atman-33/workhub --skill diagram-editgit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/diagram-edit)<a href="https://agentmods.dev/skills/atman-33/workhub/diagram-edit"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/diagram-edit/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/atman-33/workhub/diagram-edit"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/diagram-edit.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 | $0.00101 | $0.01795 |
| Opus 5.5 | $0.00040 | $0.00718 |
| Sonnet 5.5 | $0.00020 | $0.00359 |
| Haiku 4.5 | $0.00010 | $0.00179 |
Grade A, and why
diagram-edit 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 12d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram Edit
Apply a natural-language instruction to one workhub diagram note by rewriting only the affected lines.
The workhub app's Diagrams tab launches this skill with the file path and the instruction (and, in confirm mode, asks for a diff instead of a write). It also works when invoked by hand. It is the one skill for every kind of diagram: it carries the shared procedure and nothing about any single format.
Find the format first
The rule file is the source of truth for the notation. This skill does not repeat it. Read the note, then its rule, before changing a line:
-
Read the whole target file and take the frontmatter
type. -
Read the rule for that type (the vault's
.claude/rules/):typeRule to read scheduleschedules.mdmindmapmindmaps.mdmatrix2x2,flow,pfd,algorithm,usecase,architecture,ifdamdiagrams.md- the shared section and the section named after the typeThe rule normally loads on its own when you read a note under
diagrams/,schedules/ormindmaps/; a note inside a backlog item does not always trigger it, so open the file yourself when it did not appear. -
A
typethat is none of those nine, or a file with notypeoutsideschedules/andmindmaps/, is not a diagram: say so and change nothing.
A kind added to the app later works the same way: its rule names its format, and everything below still applies.
Procedure
- Identify the elements the instruction names, by title or by id. If it is ambiguous which element is meant, say so and stop - do not guess and edit.
- Work out the new content from the current file: relative instructions ("a week later", "one level up", "group these") can only be computed from what is there. Moving an element moves what hangs off it (a mindmap subtree, an element's indented note lines, its stickies stay pinned).
- Rewrite only the affected lines, in place, keeping the order of everything else.
- Validate against the rule before writing: every line you touched still
parses by the kind's grammar, ids are unchanged and unique, colours are in
the list, and no element lost a
task:link, a note line or a modifier unless the instruction asked for that. - Set
updated:to today's date in the frontmatter and leave every other key as you found it. - Write the file, then report in one paragraph: which element ids changed, from what to what, and anything you declined to do. In confirm mode, do not write: report the exact lines you would change, as a diff, and stop.
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.
- 12d ago First seen · 137 lines · 101 tokens per session scan A dc27724916e5
diagram-edit is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 1,795 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 2026-10-11.
Other skills, from other repositories
readmd-style-custom
Generate custom CSS rules and HTML head tags for ReadMD document styling.
readmd-export-style
Use when a ReadMD export needs a validated typography style represented as JSON.
expo-launchpad-design
Phase A design — define the ui/designTokens.ts spec (colors, spacing, radius, typography), the visual/component concept (game: code-drawn Skia shapes / app: RN primitives), and the asset plan (icon+splash branding, contrast-safe accessibility). Advances pipeline state to contract.
video-templates
ฉากวิดีโอที่ก๊อปไปใช้ได้เลย 75 ฉาก ไม่ใช่คำอธิบายว่าฉากควรหน้าตาแบบไหน แบ่งเป็นฉากเคลื่อนไหว 50 แบบ ครบสามอัตราส่วน — นอน 39 ตั้ง 6 จัตุรัส 5สำหรับเรนเดอร์เป็นคลิป (รวมเด็คนักลงทุนและพิตช์เด็คแบบเต็มเรื่อง กับอีก 9 ฉากในภาษาโฆษณาโปรดักต์ที่ถอดจากสเปกและจากการหยุดเฟรมดูคลิปจริง สี่ในนั้นเคลื่อนด้วยสปริงจริงของ Material…
aetox-shadcn
ทำงานกับ shadcn/ui, เพิ่ม ค้น แก้ ดีบัก สไตล์ และประกอบคอมโพเนนต์/ดีไซน์ซิสเทม ผ่าน registry และ CLI พร้อมกฎที่บังคับเสมอ (className สำหรับ layout ไม่ใช่สไตล์, ใช้ gap ไม่ใช่ space-x/y, size- เมื่อกว้างเท่าสูง, semantic colors, cn()) ใช้ตอนโปรเจกต์มี components.json หรือทำงานกับ shadcn/Tailwind/Base UI, "shadcn init"…
aetox-slide-templates
เทมเพลตจริงที่ก๊อปไปใช้ได้เลย ไม่ใช่คำอธิบายว่าควรหน้าตาแบบไหน เลย์เอาต์สไลด์ 41 แบบ รวมไดอะแกรม 16 แบบที่วาดด้วย CSS กับ SVG ในไฟล์เอง ชุดสี 6 โทนใน themes/ และม่านบนภาพ 5 แบบใน overlays/ ที่สลับได้ด้วยการเปลี่ยนบล็อก :root บล็อกเดียว กล่อง 1280x720 ไฟล์เดียวจบ ไม่มี CSS ภายนอก ไม่มีสคริปต์ ไม่มีกราฟจาก CDN…