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 Peeyushmeher/agent-agile --skill aa-helpgit clone --depth 1 https://github.com/Peeyushmeher/agent-agileWrote 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/peeyushmeher/agent-agile/aa-help)<a href="https://agentmods.dev/skills/peeyushmeher/agent-agile/aa-help"><img src="https://agentmods.dev/badge/skills/peeyushmeher/agent-agile/aa-help/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/peeyushmeher/agent-agile/aa-help"><img src="https://agentmods.dev/badge/skills/peeyushmeher/agent-agile/aa-help.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 | $0.00058 | $0.00615 |
| Opus 5 | $0.00029 | $0.00308 |
| Sonnet 5 | $0.00012 | $0.00123 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
aa-help 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 9d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aa-help
Read-only. Answer directly from this file — never dispatch a subagent and never read a playbook for this command.
The funnel
Every project moves through the same funnel, front door to first demo:
rough idea → grill → intake → plan → panel → prereqs → waves → demo
Commands
| Command | Purpose |
|---|---|
/aa-grill |
Idea interrogation → IDEA.md (can reject the idea) |
/aa-new-project |
8-question intake → OKRs → epics → Epic 1 stories |
/aa-import |
Existing plan: audit → gaps → panel → proceed/reshape/kill |
/aa-panel |
Run the critic panel on the current draft plan |
/aa-plan-epic |
Slice next epic: contracts scope + story cards + waves |
/aa-execute-epic |
Wave 0 → collision check → Wave 1 → Wave 2 |
/aa-review |
Present DEMO.md → approve/redo/replan |
/aa-autopilot |
Chain all epics; --gate full-auto|checkpoint |
/aa-resume |
Read STATE.md, pick up the baton |
/aa-status |
Where are we; roadmap + KR progress |
/aa-help |
Command guide + methodology crash course |
The methodology, in five lines
- Work breaks down OKR → Initiative → Epic → Story and stops there — no level below a story, no story points, no burndown.
- Every epic's definition of done is one demo sentence: "I can do X and see Y" — if you can't write that sentence, the epic isn't scoped yet.
- A critic panel attacks the plan before execution, and a human shopping list (
PREREQS.md) blocks any run that needs a key, account, or service it doesn't have yet. - Story cards are sized so a cheap-tier agent can finish one from just its card plus the frozen contracts — zero exploring, zero guessing intent.
- Every epic ends at a review gate with exactly three outcomes: approve, redo (feedback becomes new acceptance checks, never a vague note), or replan (back to slicing).
If the user names a specific command, point them at it and its one-line purpose from the table above. If they're unsure where to start, point them at the front door that matches what they're bringing: a vague spark → /aa-grill, a clear idea → /aa-new-project, an existing plan or spec → /aa-import.
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.
- 9d ago First seen · 44 lines · 58 tokens per session scan A aeae5b1565c9
aa-help is a skill published in the GitHub repository Peeyushmeher/agent-agile (3 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 615 once invoked, about $0.0003 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
project-manager
This skill has been upgraded with agentic AI capabilities, OKR/KPI integration patterns, and async-first workflows based on 2026 PM best practices research.
product-frameworks
Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when building ROI projections, competitive analysis, RICE scoring, OKR trees, user personas, PRDs, or usability testing plans.
skill-refinement
A review tool for measuring how well other skills work over time. It examines task records, unresolved questions, costs, failures, repeated work, and changes in confidence.
workflow-refinement
A post-workflow review process that examines how stages depend on one another and how information is handed between them.
run-team-retrospective
Use when a team needs to reflect on a completed period, project, or significant event — to extract what worked, what didn't, and what specific changes to make before the next cycle, rather than repeating the same patterns.
culture-architect
Build, measure, and evolve company culture as operational behavior, not wall posters. Use when building company values, assessing culture health, designing rituals, creating culture codes, or handling culture clashes.