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 OdinMB/ops-workflow --skill scaffoldgit clone --depth 1 https://github.com/OdinMB/ops-workflowWrote 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/odinmb/ops-workflow/scaffold)<a href="https://agentmods.dev/skills/odinmb/ops-workflow/scaffold"><img src="https://agentmods.dev/badge/skills/odinmb/ops-workflow/scaffold/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/odinmb/ops-workflow/scaffold"><img src="https://agentmods.dev/badge/skills/odinmb/ops-workflow/scaffold.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 | $0.00030 | $0.02888 |
| Opus 5.5 | $0.00012 | $0.01155 |
| Sonnet 5.5 | $0.00006 | $0.00578 |
| Haiku 4.5 | $0.00003 | $0.00289 |
Grade A, and why
scaffold 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 today.
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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ops Scaffold
Set up a new non-code project management repo, or adjust an existing one to match the ops conventions.
Detect Mode
Check the current directory:
- If
CLAUDE.mdexists → Adjust mode: read it, compare against the template below, and propose specific changes. Don't overwrite — use Edit to patch. Ask before creating missing folders. - If no
CLAUDE.md→ New repo mode: run the full interview and scaffold from scratch.
Interview (New Repo Mode)
Ask the user:
- Project name — what the project is called
- One-paragraph description — what the project does, who it's for
- Constraints — team size, budget, timeline, key limitations
- The charter — one topic at a time, offering your best guess from what they've said, and reading each answer back before you write it: who the project is for and the job they need done; 2-4 goals for the near term, each with how they'd know it is working; the audiences those goals target beyond the people it's for (a funder, a partner, a would-be maintainer); non-goals; what they care about and won't trade away; how bold to be. These become
charter.md - Initial domain areas — what topics will the project cover? These become the initial subfolders. Examples:
- Marketing, legal, fundraising, partnerships, technical research
- Or more specific: grants, audience growth, competitor analysis
- Connected to a coding repo? — ask if this ops repo is paired with a codebase. If yes, ask for the relative path from this repo to the code repo root (e.g.,
../if sibling directories,../app/if nested). This enables read-only access to the code for context.
Interview (Adjust Mode)
Read the existing structure (CLAUDE.md, MEMORY.md, folder listing). Then ask:
- What needs changing? — or just check against the template and propose fixes
- Missing folders? — offer to create any missing standard folders with INDEX.md files
- CLAUDE.md drift? — show specific differences from the template and offer to patch. An
## Autopilotsection, which autopilot's setup writes, is not drift: leave it as it is. Anautopilot/folder is autopilot's memory from before it moved into this layout: leave it, and suggest running autopilot in a session started from the code repo, which moves it - No
charter.md? — a repo set up before it existed keeps its goals in MEMORY.md, under "Constraints & Goals". Offer to move them into a newcharter.md(template below), asking for what the template needs and MEMORY.md doesn't say, and to leave the constraints in MEMORY.md with the pointer line from its template. Where anautopilot/folder exists, leave this to autopilot's move, which merges its own charter in
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.
- today Changed · +41 lines adc99dbe97c4
- yesterday Changed d27ec6357c4d
- 2d ago Changed 71642e6299c5
- 1mo ago First seen · 275 lines · 30 tokens per session scan A 19dde148df95
scaffold is a skill published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 2,888 once invoked, about $0.0001 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.
Other skills, from other repositories
factory-voice
Communication voice for Claude Code — senior software architect, first-principles framing, crisp English. Governs how Claude writes to Linear (issue comments, summaries, status updates), commits, PRs, and how it talks in terminal sessions. Read on session start and before any external write.
factory-close
Close out a Linear issue — move to Done, add a closing comment, and clean up the local branch/worktree.
factory-submit
Move the current branch's Linear issue to "In Review".
factory-setup-linear
Configure portable Linear workflow settings in .factory-kit/linear.json, migrating legacy .claude/linear.json settings when present.
synergy-tracker
Manage cross-project synergy tracking between sibling projects. Use when the user wants to log a shared pattern, a divergence, an extraction candidate, or something a sibling project has that this one doesn't. Also use when the user wants to promote synergy entries to Basic Memory (workflow 5). NOT for upstream…
upstream-tracker
Manage upstream issue tracking for this project. Use when the user wants to log a bug or friction point in a vendor package or npm dependency, review open upstream items, resolve a tracked issue, run a trend review, generate the upstream observations section of a sprint retrospective, promote upstream observations to…