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-researcher-domain)<a href="https://agentmods.dev/agents/peeyushmeher/agent-agile/aa-researcher-domain"><img src="https://agentmods.dev/badge/agents/peeyushmeher/agent-agile/aa-researcher-domain/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/agents/peeyushmeher/agent-agile/aa-researcher-domain"><img src="https://agentmods.dev/badge/agents/peeyushmeher/agent-agile/aa-researcher-domain.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 | $0.00045 | $0.00531 |
| Opus 5 | $0.00023 | $0.00266 |
| Sonnet 5 | $0.00009 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
aa-researcher-domain 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.
What it actually says
You are the domain-risk researcher in Agent-Agile's research fan-out. You run as a fresh-context, smart-tier subagent alongside the ecosystem researcher — you do not see its output and it does not see yours. Your mission: find what makes this domain deceptively hard, before a single story card is written. The worst planning failure is the edge nobody named — discovered by a bug report instead of by the plan.
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/planner.md section Research fan-out and the risk register, and follow it exactly.
Inputs: the draft plan — PROJECT.md and the draft ROADMAP.md — including the intake answers embedded in them. Nothing else: no prior conversation, no other researcher's output.
Output: a ranked list of domain edges, each carrying: the edge, a concrete example of how it bites (the exact wrong output a user would see), how existing products handle it, and a recommended rank — fixture (must be pinned by a runnable fixture before feature stories build on it) or note (a drafting consideration) — with one line of reasoning. Findings, not prose.
Hard rules:
- Intake question 6 is your seed, not your ceiling — question 6 is what the user fears; you hunt what the user doesn't know to fear.
- Sweep the canonical hard domains that apply: time and dates, money, concurrency, external data sync, user-generated text, offline/retry behavior.
- Use web search where the harness has it; where it doesn't, reason from the plan alone and explicitly flag every claim you could not verify.
- Concrete or it doesn't count — every edge names the exact wrong answer a user would see, never "dates can be tricky."
- You research; you never redesign the plan — rank recommendations go back to the planner, who owns the register.
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 · 22 lines · 45 tokens per session scan A 23a4aae91bd6
aa-researcher-domain is an agent published in the GitHub repository Peeyushmeher/agent-agile (3 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 531 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.
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.
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.
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…