solve

solve is a skill for Claude Code, Codex from maxbaluev/accreted-intelligence. It costs 28 tokens per session (251 once invoked), scanned A, original, Apache-2.0.

A skill that sends a goal through a scored-memory reasoning process and handles the returned deliberation.

In plain words
What is it for?
Use it to solve goals through the acc system, submit a proposal when asked, and close the recorded commitment with an outcome.
Why use it?
It provides a defined process for retrieving context, considering an intermediate result, and recording whether the answer later proved useful.

Skill for Claude CodeCodex

Part of the acc plugin — 3 skills, 8 hooks, 1 MCP server 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 skills/maxbaluev/accreted-intelligence/solve
Any agent
npx skills add maxbaluev/accreted-intelligence --skill solve
Clone the repo
git clone --depth 1 https://github.com/maxbaluev/accreted-intelligence

Made for: Claude Code, Codex.

Or install acc, the plugin that ships this one along with the rest of its 3 skills, 8 hooks, 1 MCP server.

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 solve

README.md
[![agentmods](https://agentmods.dev/badge/skills/maxbaluev/accreted-intelligence/solve.svg)](https://agentmods.dev/skills/maxbaluev/accreted-intelligence/solve)
Your own site
<a href="https://agentmods.dev/skills/maxbaluev/accreted-intelligence/solve"><img src="https://agentmods.dev/badge/skills/maxbaluev/accreted-intelligence/solve.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 251 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 $0.00028 $0.00251
Opus 5 $0.00014 $0.00125
Sonnet 5 $0.00006 $0.00050
Haiku 4.5 $0.00003 $0.00025

Measured 3d ago against content hash 643f38564c30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

solve 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 3d 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.

plugins/claude/skills/solve/SKILL.md · 19 lines

What it actually says

solve

Routing sugar over the two MCP verbs — no logic lives here.

  1. Call acc_act(runtime="solve", input="<the goal>").
  2. If the result is final: surface the answer, the commitment id, and the cited [ids].
  3. If the result is a brain_frame: it is YOUR deliberation turn — the frame is typed (which hole, what was retrieved, what is predicted). Reason over it, then submit via acc_act(runtime="continue", input={"frame_id": ..., "submit_token": ..., "proposal_text": ...}).
  4. End proposal_text with PREDICT: <0.00-1.00> <why>; acc strips that line before the owner sees it and uses it to calibrate the Work Model against later outcomes.
  5. Never leave a received frame unresolved; never solo-derive outside the loop.
  6. Close the commitment honestly later with acc_act(runtime="outcome", ...).
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. 3d ago First seen · 19 lines · 28 tokens per session scan A 643f38564c30

Subscribe to this mod's changes

solve is a skill published in the GitHub repository maxbaluev/accreted-intelligence (7 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 251 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

kayba-ace

This skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.

kayba-ai/agentic-context-engine · 0 tokens

plur-memory

Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.

plur-ai/plur · 31 tokens

plur-memory

Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use.

plur-ai/plur · 41 tokens

lemmalog

Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…

JordyZomer/lemmalog · 105 tokens

honcho-integration

Integrate Honcho memory into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, and accessing Honcho's representation.

plastic-labs/honcho · 40 tokens

honcho-memory

Concepts and strategy for using a connected Honcho as persistent memory of the user — the recall/record loop and session and peer design. Start here to understand how Honcho memory works, then connect — via a first-class integration for your environment if one exists (preferred), or raw MCP tools (covered here) or the…

plastic-labs/honcho · 91 tokens