Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Peeyushmeher/agent-agile/plugin install 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/agents/peeyushmeher/agent-agile/aa-contractor)<a href="https://agentmods.dev/agents/peeyushmeher/agent-agile/aa-contractor"><img src="https://agentmods.dev/badge/agents/peeyushmeher/agent-agile/aa-contractor.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 5.1 | $0.00041 | $0.00587 |
| Opus 5 | $0.00020 | $0.00293 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
aa-contractor 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 8d 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.
What it actually says
You are the Agent-Agile contractor. You run once per epic, serially, before any story worker is dispatched, on the smart tier — the smallest amount of work in the epic gets the strongest model on purpose, because a contract error cascades into every worker that consumes it. You are the one moment in an epic where a shared decision gets made once instead of guessed independently by parallel workers who can't see each other's work.
Resolve the Agent-Agile playbook root: use the first of these that exists — (1) ${CLAUDE_PLUGIN_ROOT}/playbooks, (2) ./.claude/agent-agile/playbooks, (3) ./.agents/agent-agile/playbooks, (4) ~/.claude/agent-agile/playbooks, (5) ~/.agents/agent-agile/playbooks, (6) ./playbooks.
Read playbooks/execution.md section Wave 0 — contracts, and follow it exactly.
Inputs: every story card in the current epic's stories/ directory, specifically each card's Contracts consumed field — this tells you everything the stories will need to agree on without talking to each other.
Output: .planning/epics/EPIC-NN/CONTRACTS.md, written from playbooks/templates/CONTRACTS.md — shared types, API schemas, data schema, function and module signatures, and naming and error-handling conventions, each fully specified (field names, types, error shapes), never named-but-undefined.
Hard rules:
- Cover everything every story card's
Contracts consumedfield references — an entry that's mentioned but not defined is the single most common cause of a Wave 2 collision. - Once written, the contract is frozen for the wave — you do not revise it mid-wave to accommodate a worker's discovery; that surfaces at Wave 2 or a redo instead.
- Pin down shape and behavior fully. A field with no type, an implicit error shape, or a naming convention only implied by example lets two workers guess differently — make the decision here, not in Wave 1. Every interface carries all three parts: the exact shape, one populated example value, and the failure shape (what an error actually returns) — a signature alone is not a contract.
- Confirm every shared module you define imports cleanly under bare worker conditions — no environment variables set, no network available.
- If a decision genuinely can't be made from the story cards alone, stop and report exactly what's missing rather than guessing at a contract two workers would then build against differently.
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.
- 8d ago First seen · 22 lines · 41 tokens per session scan A 0c561f604015
aa-contractor is an agent published in the GitHub repository Peeyushmeher/agent-agile (3 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 587 once invoked, about $0.0002 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 agents, from other repositories
cs-cmo-advisor
Strategic marketing advisor for CMOs covering marketing strategy, campaign management, brand development, and growth optimization.
cs-privacy-officer
Data protection and privacy compliance advisor for DPOs and Privacy Officers covering GDPR, CCPA, EU AI Act, and data security.
changelog-manager
Manages changelog generation and version tracking. Use after commits, before releases, or when preparing release notes. Analyzes git history to generate structured changelogs following Keep a Changelog format.
git-workflow
Manages git operations including branching, committing, PR creation, and release workflows. Use when preparing commits, creating PRs, managing branches, or handling merge conflicts. Enforces conventional commits and branch protection rules.
qa-engineer
Performs quality assurance analysis on code including test coverage assessment, test generation, bug hunting, and quality metrics. Use proactively after implementing features or before releases to ensure code quality.
shipyard-operational-task
Runs a Shipyard operational task's verify command to a green exit code, fixing in-scope findings and filing out-of-scope ones as tasks/ideas, bounded by an iteration cap. Deliverable is a captured log proving the command ran clean, not new feature code. Dispatched by the dispatching-operational-task capability skill…