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 agentmods add commands/sawrus/agent-guides/featuregit clone --depth 1 https://github.com/sawrus/agent-guidesWrote 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/commands/sawrus/agent-guides/feature)<a href="https://agentmods.dev/commands/sawrus/agent-guides/feature"><img src="https://agentmods.dev/badge/commands/sawrus/agent-guides/feature.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.00718 |
| Opus 5 | $0.00005 | $0.00359 |
| Sonnet 5 | $0.00002 | $0.00144 |
| Haiku 4.5 | $0.00001 | $0.00072 |
Grade A, and why
feature 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 yesterday.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feature - Create New Feature
This command executes an SDLC workflow with explicit subagent ownership per step.
Roles
- Primary: @product-owner
- Subagents: @pm, @team-lead, @designer, @developer, @qa
RACI-lite
| Step | Responsible | Accountable | Consulted |
|---|---|---|---|
| Scope definition | @product-owner, @pm | @product-owner | @team-lead, @designer |
| Technical/design planning | @team-lead, @designer | @team-lead | @pm, @qa |
| Delivery planning | @pm | @pm | @product-owner, @team-lead |
| Implementation | @developer | @team-lead | @qa, @designer |
| Verification | @qa | @qa | @developer, @team-lead |
| Final acceptance | @product-owner | @product-owner | @pm, @team-lead, @qa |
Workflow Steps
Step 1 — Scope and Success Criteria
- Owner: @product-owner + @pm
- Inputs: stakeholder request, constraints, context
- Actions: define scope, outcomes, acceptance criteria, non-goals
- Outputs:
docs/<feature_name>/README.md - Done: acceptance criteria are testable and approved for planning
Step 2 — Technical and UX Plan
- Owner: @team-lead + @designer
- Inputs: approved scope
- Actions: architecture and UX approach, risks, milestones, quality gates
- Outputs:
implementation_plan.md,design_brief.md, optional diagrams - Done: approach is feasible and reviewable
Step 3 — Delivery Plan and Alignment
- Owner: @pm
- Inputs: plan artifacts from Step 2
- Actions: sequence tasks, define handoffs, confirm schedule/risk handling
- Outputs:
delivery_plan.md,risk_register.md - Done: stakeholder confirms plan and priorities
Step 4 — Implementation Increment
- Owner: @developer
- Inputs: approved implementation/design/delivery plans
- Actions: implement scope slice, add/update tests, run quality checks
- Outputs: code changes + test evidence + implementation notes
- Done: ready for QA + Team Lead review
Step 5 — Verification and Review
- Owner: @qa + @team-lead
- Inputs: implementation increment
- Actions: execute verification strategy, review architecture/code quality, classify findings
- Outputs: test report, review feedback, blocker list
- Done: either accepted or sent back with actionable fixes
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.
- yesterday First seen · 76 lines · 11 tokens per session scan A c4c4d45de926
feature is a command published in the GitHub repository sawrus/agent-guides (17 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 718 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 2026-09-03.
Other commands, from other repositories
planning
Break work into small verifiable tasks with acceptance criteria and dependency ordering.
planning
将工作拆解为带 acceptance criteria 和 dependency ordering 的小型可验证 tasks.
webperf
Run a web performance audit via the web-performance-auditor persona.
newpkg
Generate new package with Nx.
sddp-prd
Create or refine the canonical product document.
to-done
Command "to-done" from eyaltoledano/claude-task-master, covering completing a task, pre-completion checks, execution, post-completion actions and celebration & learning.