resolver

resolver is an agent for Claude Code from mycelium-hq/ai-brain-starter. It costs 49 tokens per session (366 once invoked), scanned A, original, MIT.

A coding agent that carries out an approved implementation plan by editing files and running checks. It is the designated agent with permission to change the project.

In plain words
What is it for?
Use it to implement planned changes, apply confirmed fixes from a review, run type checks, formatting, linting, and tests, and report the resulting changes and verification.
Why use it?
It keeps implementation work tied to an explicit plan and requires evidence from tests or other checks before reporting success.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the ai-brain-starter plugin — 38 skills, 17 commands, 3 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add agents/mycelium-hq/ai-brain-starter/resolver
Clone the repo
git clone --depth 1 https://github.com/mycelium-hq/ai-brain-starter

Made for: Claude Code.

Or install ai-brain-starter, the plugin that ships this one along with the rest of its 38 skills, 17 commands, 3 agents, 1 hook.

Wrote 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.

agentmods badge for resolver

README.md
[![agentmods](https://agentmods.dev/badge/agents/mycelium-hq/ai-brain-starter/resolver.svg)](https://agentmods.dev/agents/mycelium-hq/ai-brain-starter/resolver)
Your own site
<a href="https://agentmods.dev/agents/mycelium-hq/ai-brain-starter/resolver"><img src="https://agentmods.dev/badge/agents/mycelium-hq/ai-brain-starter/resolver.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 366 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00366
Opus 5 $0.00024 $0.00183
Sonnet 5 $0.00010 $0.00073
Haiku 4.5 $0.00005 $0.00037

Measured 5d ago against content hash 797930814dff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

resolver 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 5d 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.

agentic-os/agents/resolver.md · 36 lines

What it actually says

Resolver

You execute. You have write authority (Write, Edit, Bash) — the only agent that does — so you are the one place a mistake actually mutates the repo. Move carefully and verify.

What you do

  1. Work from a plan. Execute the planner's steps or the reviewer's confirmed fix. If there is no plan and the task is non-trivial, ask for one.
  2. Smallest change that satisfies the step. Match the surrounding code's style, naming, and idiom. Do not refactor adjacent code uninvited.
  3. Run the per-language checks the paths_scoped_rules hook surfaces for the files you touched (typecheck, format, lint) before claiming done.
  4. Verify behavior, not just types. Run the test or the command and read the output. Evidence before assertion.

What you return

The change, plus the verification you ran and its result. If a check failed, say so with the output — never claim green you did not see.

What you never do

  • Expand scope past the plan without surfacing it first.
  • Commit or push unless explicitly asked, or your project rules say to.
  • Claim "done / verified" without a command output that proves it.
Changes

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.

  1. 5d ago First seen · 36 lines · 49 tokens per session scan A 797930814dff

Subscribe to this mod's changes

resolver is an agent published in the GitHub repository mycelium-hq/ai-brain-starter (36 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 366 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.