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 HawkannG/Claude-Warden --skill warden-workflowgit clone --depth 1 https://github.com/HawkannG/Claude-WardenWrote 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/hawkanng/claude-warden/warden-workflow)<a href="https://agentmods.dev/skills/hawkanng/claude-warden/warden-workflow"><img src="https://agentmods.dev/badge/skills/hawkanng/claude-warden/warden-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/hawkanng/claude-warden/warden-workflow"><img src="https://agentmods.dev/badge/skills/hawkanng/claude-warden/warden-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 | $0.00023 | $0.02581 |
| Opus 5 | $0.00012 | $0.01290 |
| Sonnet 5 | $0.00005 | $0.00516 |
| Haiku 4.5 | $0.00002 | $0.00258 |
Grade A, and why
warden-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 10d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow Protocol
Policy Area: WORK Version: 1.2 Status: Active Enforcement: MUST (per RFC 2119) Purpose: How every feature, fix, and change moves from idea to shipped code with Claude Code. Includes mandatory UAT checkpoints at each phase.
1. The Five Phases
Every unit of work follows five phases. No phase can be skipped.
PROPOSE → PLAN → BUILD → VERIFY → CLOSE
2. Phase 1: PROPOSE
Who leads: Human What happens: Human describes what they want. Claude asks clarifying questions. No code, no files yet.
Claude MUST:
- Restate the request in one sentence to confirm understanding
- Ask 2-5 clarifying questions about scope, edge cases, and constraints
- Identify which governance files are relevant
- Flag anything that conflicts with CLAUDE.md constraints or active directives
- NOT write any code, NOT create any files
UAT Checkpoint — PROPOSE:
- Ask: "Is this user-facing?" If yes:
- "What are the acceptance criteria? Are there existing test cases in your test management tool?"
- If no acceptance criteria exist: define them now, in business language, before proceeding
- Acceptance criteria must include: happy path, at least one edge case, expected error states
- Write criteria in plain language ("User sees X") not code ("returns 200")
Gate: PROPOSE → PLAN
Human says: "Plan it" or any clear affirmative. For user-facing features, acceptance criteria must exist before this gate opens.
If human says "just do it": Claude responds: "Let me give you a 30-second plan first so we don't build the wrong thing. Here's what I'd do: [quick plan]. Sound good?"
3. Phase 2: PLAN
Who leads: Claude What happens: Claude produces a structured plan. Human reviews and approves.
Claude MUST produce:
## Plan: [Feature/Fix Name]
**Scope:** [One sentence]
**Touches:** [Governance areas affected]
**Acceptance Criteria:** [List from PROPOSE, or reference test case IDs]
### Files to Create
- path/to/file.ts — purpose
### Files to Modify
- path/to/existing.ts — what changes and why
### Files NOT Touched
- [Explicitly list to prevent scope creep]
### Governance Updates Required
- [ ] Which docs need updating and why
### Risks & Decisions
- [Anything needing human input]
### Estimated Scope
- Files: [count] | Complexity: Low / Medium / High
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.
- 10d ago First seen · 289 lines · 23 tokens per session scan A 575cbd766393
warden-workflow is a skill published in the GitHub repository HawkannG/Claude-Warden (2 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 2,581 once invoked, about $0.0001 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
memstack-business-client-onboarding
Use this skill when the user says 'client onboarding', 'new client', 'onboard client', 'kickoff meeting', 'intake form', 'welcome email', or needs welcome sequences, questionnaires, and setup checklists for new clients. Do NOT use for contracts or invoicing.
memstack-product-roadmap-builder
Use this skill when the user says 'roadmap', 'product roadmap', 'quarterly plan', 'now/next/later', 'OKRs', or needs strategic planning with themes, milestones, resource allocation, and stakeholder-ready views. Do NOT use for MVP scoping or sprint-level planning.
memstack-product-user-story-generator
Use this skill when the user says 'user stories', 'write stories', 'backlog', 'sprint planning', 'acceptance criteria', or needs prioritized stories with Given/When/Then criteria and story point estimates. Do NOT use for full PRDs or detailed feature specs.
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
ops-desk
Operate a project, workspace, or account from an agent or manager dashboard: inspect state, triage risks, prepare governed actions, route to the right skill lane, require approvals for consequential acts, and verify receipts after execution.
business-ops
Route one business signal through a replayable governed ops graph: classify, docs, release, work, outreach, spend, and proof, with consequential actions stopping at the right gate.