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 charlesdove977/procedure-ops --skill skillgit clone --depth 1 https://github.com/charlesdove977/procedure-opsWrote 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/charlesdove977/procedure-ops/skill)<a href="https://agentmods.dev/skills/charlesdove977/procedure-ops/skill"><img src="https://agentmods.dev/badge/skills/charlesdove977/procedure-ops/skill/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/charlesdove977/procedure-ops/skill"><img src="https://agentmods.dev/badge/skills/charlesdove977/procedure-ops/skill.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 | $0.00112 | $0.01391 |
| Opus 5.5 | $0.00045 | $0.00556 |
| Sonnet 5.5 | $0.00022 | $0.00278 |
| Haiku 4.5 | $0.00011 | $0.00139 |
Grade A, and why
sop-build 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
- Delegating a recurring task to a VA, contractor, or new hire
- Documenting a process you keep redoing from scratch
- Identifying which steps in a process can be automated (then feeding into n8n / Zapier / Make / managed agent)
- Onboarding documentation for a new role or seat
- Auditing or cleaning up an existing SOP
Not For
- Building the automation itself — that is a separate job after the SOP flags it. Hand off to
/seed:tasks:ideateto incubate, then/paul:planto build. - Project plans with milestones — use the
paul:*workflow skills - Ideating brand new processes that do not yet exist — use
seed:*for incubation - Client-facing deliverables, proposals, sales copy — use
ccpdforcopywriting
Style
- Structured and opinionated. Challenges weak inputs.
- Uses frameworks by name (RACI, BPMN, swim-lane) when relevant.
- Drills into hidden steps, exceptions, and handoff points.
- Plain language. Ninth-grade reading level by default. No jargon unless the user is already using it.
- Pushes for precision: replaces "review the form" with "open the form, check fields X, Y, Z, confirm they match the contract."
Expertise
- Standard operating procedure design (BPMN, swim-lanes, RACI)
- Operational delegation and handoff design (writing SOPs so a VA or new hire can execute without you)
- Workflow automation routing (n8n, Make, Zapier, Claude managed agents) — flagging which steps belong in which tool
- Quality control and inspection checkpoints inside procedures
What ships with it
17 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.
- checklists/automation-readiness.md 3.5 KB
- checklists/handoff-completeness.md 3.5 KB
- checklists/sop-ready-to-delegate.md 3.2 KB
- frameworks/automation-flagging.md 7.0 KB
- frameworks/hosting-options.md 5.3 KB
- frameworks/raci-matrix.md 3.0 KB
- frameworks/sop-anatomy.md 6.7 KB
- frameworks/swim-lane-format.md 3.3 KB
- tasks/audit.md 2.9 KB
- tasks/delegate-pack.md 4.3 KB
- tasks/from-recording.md 2.8 KB
- tasks/interview.md 7.9 KB
- tasks/scaffold-business.md 5.6 KB
- templates/delegate-packet.md 3.3 KB
- templates/interview-transcript.md 2.7 KB
- templates/sop-audit-report.md 2.9 KB
- templates/sop-document.md 2.9 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.
- 2mo ago First seen · 98 lines · 112 tokens per session scan A f10e7dffbb41
sop-build is a skill published in the GitHub repository charlesdove977/procedure-ops (62 stars, last pushed 14d ago), licensed MIT. It adds 112 tokens to every session and 1,391 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 2026-08-30.
sop-build compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sop-buildcharlesdove977/procedure-ops | Skill | 62 | 14d ago | MIT | A | 112 | Claude Code |
| status-card-querypaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 40 | Claude Code, Codex |
| 360-feedback-systemsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 45 | Claude Code |
| admin-access-registersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 49 | Claude Code |
| access-matrixsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 41 | Claude Code |
| advanced-analytics-dashboardsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| alumni-re-hire-trackersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 54 | Claude Code |