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 Gekkos-tech/agency-os --skill agency-workflowgit clone --depth 1 https://github.com/Gekkos-tech/agency-osWrote 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/gekkos-tech/agency-os/agency-workflow)<a href="https://agentmods.dev/skills/gekkos-tech/agency-os/agency-workflow"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/agency-workflow/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/gekkos-tech/agency-os/agency-workflow"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/agency-workflow.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 | $0.00199 | $0.01337 |
| Opus 5 | $0.00100 | $0.00668 |
| Sonnet 5 | $0.00040 | $0.00267 |
| Haiku 4.5 | $0.00020 | $0.00134 |
Grade A, and why
agency-workflow 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 11d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agency Workflow
The project spine for web agencies. Every client project moves through six phases. This skill decides which phase you are in, which specialist skill to load, and which gate must pass before the next phase. It never does the specialist work itself — it routes.
Operating principles
- Plan before code. No production code before the plan for that increment is stated and (for client work) approved. State what will be built, from which design source, touching which files.
- One source of truth for design. If a design handoff exists (design images, a style guide, a token file, a Figma export), it IS the design — never regenerate colors/typography/layout that the handoff already defines. Quality skills then act as reviewers, not generators. Only without a handoff may a design system be generated fresh.
- Scope discipline. Do what the current phase requires, nothing from a later phase. Surface scope changes instead of silently absorbing them.
- Every phase has an exit gate. Do not advance until the gate checklist for the phase passes (see the phase reference files).
Phase detection
Check docs/project-state.md first — if it exists, it names the current
phase, open blockers, and what the client owes; trust it over re-derivation.
If it's missing or stale, classify from project signals:
| Signal | Phase |
|---|---|
| New client/goal mentioned, no brief document yet | BRIEF |
| Brief exists; no sitemap/direction/offer yet | CONCEPT |
| Concept approved; no visual design/handoff yet | DESIGN |
| Design source exists; code missing or incomplete | BUILD |
| Feature-complete; not yet verified | QA |
| QA passed; not yet live / launch requested | LAUNCH |
| Site is live; monitoring, updates, reports, "did anything break" | MAINTAIN |
If the user's request names a later phase but earlier gates never happened (e.g. "build the site" with no brief), do a compressed pass of the earlier phases first — a 5-line mini-brief beats none — and say so.
What ships with it
8 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.
- 11d ago First seen · 83 lines · 199 tokens per session scan A 8d5ed39682af
agency-workflow is a skill published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 2mo ago), licensed MIT. It adds 199 tokens to every session and 1,337 once invoked, about $0.0010 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
azure-devops
Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…
atlassian
Manage Jira issues and Confluence wiki pages in Atlassian Cloud. Use when: (1) searching/creating/updating Jira issues with JQL, (2) searching/reading/creating Confluence pages with CQL, (3) managing Jira workflows, transitions, and comments, (4) browsing Confluence spaces and page hierarchies. Supports OAuth 2.1 via…
jira-workflow
Orchestrate Jira workflows end-to-end. Use when building stories with approvals, transitioning items through lifecycle states, or syncing task completion with Jira.
migration-tracker
Context for ongoing migration from old Portfolio Buddy app. Use when: fixing bugs, adding migrated features, checking feature parity, or understanding why certain code exists. Contains list of 40 features being migrated and known issues.
jira-safe
Implement SAFe methodology in Jira. Use when creating Epics, Features, Stories with proper hierarchy, acceptance criteria, and parent-child linking.
linear
Manages Linear issues, teams, and projects via CLI. Lists issues, creates tasks, views details, links issues, and runs GraphQL queries. Must use for "my Linear issues", "create Linear task", "link issues in Linear", "Linear API query", or any Linear project management request.