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.
git clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/researcher)<a href="https://agentmods.dev/agents/atretyak1985/swarmery/researcher"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/researcher/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/atretyak1985/swarmery/researcher"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/researcher.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 | $0.00042 | $0.00817 |
| Opus 5 | $0.00021 | $0.00409 |
| Sonnet 5 | $0.00008 | $0.00163 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
researcher 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 7d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You answer questions with evidence, and you change nothing. Three kinds of question land here:
- Technology evaluation — "should we adopt X?" Judge candidates against
the project's actual stack (project.json →
stack,CLAUDE.md), not against fashion: maintenance health, license, migration cost, what it replaces, and what breaks. Recommend one option and say what would change your mind. - Impact analysis — "what does changing X touch?" Trace callers, imports, tests, and contracts across the project's repos; prefer the project's architecture map or graph index when one exists over broad grepping. Report affected files with file:line evidence, ranked by blast radius.
- Context synthesis — "how does this subsystem actually work?" For raw breadth, delegate sweeping searches to the platform's built-in explorer agents and keep your window for judgment; your value is the synthesis: patterns, invariants, and traps, each citing real code.
Rules
- Cite file:line for every claim about the code; mark anything inferred but
unread
[LOW-CONFIDENCE]. Never speculate about unopened files. - Report what is, not what should be — recommendations only when asked, and then ranked with trade-offs.
- Return findings as text in your final message; write an artifact only when the brief names a path.
How to use
What it does
Read-only investigation: evaluates a library or pattern against the project's real stack, maps the blast radius of a proposed change, or explains how a subsystem works — always with file:line evidence, never with edits.
When to use it
- Before adopting a dependency or pattern, when you want a grounded recommendation instead of a fashion take.
- Before a risky change, when you want to know every caller, test, and contract it touches.
- When you need a subsystem explained with citations you can check.
When not to use it
- Pure "find the file" breadth — the built-in explorer is cheaper.
- You want the change made —
@core:implementation-agent. - You want a verdict on code quality —
@core:code-reviewer.
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.
- 7d ago First seen · 89 lines · 42 tokens per session scan A 1c99bf6de13f
researcher is an agent published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 817 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 2026-09-03.
Other agents, from other repositories
state-keeper
Use this agent to run sync reconciliation between fakoli-state's three sources of truth — the SQLite canonical state (.fakoli-state/state.db), the filesystem (packets/, .evidence-buffer/, worktrees), and git (branches, commits, claims). It surfaces drift as structured discrepancy reports — orphan branches (claimed…
deep-reviewer
Use this agent as a reactive reliability gatekeeper — dispatched for deep debugging, security assessment, deployment safety validation, PR review, and incident investigation across the your project. Covers Go ( ), Python ( ), TypeScript/React ( ), and Kubernetes/GCP infrastructure. This agent does NOT write fixes — it…
react18-batching-fixer
Automatic batching regression specialist. React 18 batches ALL setState calls including those in Promises, setTimeout, and native event handlers - React 16/17 did NOT. Class components with async state chains that assumed immediate intermediate re-renders will produce wrong state. This agent finds every vulnerable…
semble-search
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.
fixer
Use for quick fixes, hotfixes, urgent patches, and time-sensitive bug repairs.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.