deep-improvement

deep-improvement is an agent for Claude Code from MichelKerkmeester/skilled-harness__spec-driven-agent-loops. It costs 19 tokens per session (3,243 once invoked), scanned A, a copy of deep-improvement, MIT.

A restricted agent that proposes one possible improvement inside a specified experiment folder. It stops before judging, measuring, approving, or packaging that proposal.

In plain words
What is it for?
Generating bounded candidate changes for deep-improvement experiments when another process will later evaluate and promote them.
Why use it?
It keeps idea generation separate from evaluation and protects the main files and reference materials from being changed.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents; mentions Codex.

Good fit Generating bounded candidate changes for deep-improvement experiments when another process will later evaluate and promote them.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/deep-improvement
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.

Clone the repo
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-harness__spec-driven-agent-loops

Made for: Claude Code.

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 deep-improvement

README.md
[![agentmods](https://agentmods.dev/badge/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/deep-improvement/github.svg)](https://agentmods.dev/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/deep-improvement)
Your own site
<a href="https://agentmods.dev/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/deep-improvement"><img src="https://agentmods.dev/badge/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/deep-improvement/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.

agentmods 80×15 button for deep-improvement

Your own site · 80×15
<a href="https://agentmods.dev/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/deep-improvement"><img src="https://agentmods.dev/badge/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/deep-improvement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,243 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00019 $0.03243
Opus 5 $0.00010 $0.01622
Sonnet 5 $0.00004 $0.00649
Haiku 4.5 $0.00002 $0.00324

Measured 9d ago against content hash d85eebc422a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deep-improvement 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 9d 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.

Origin

This is a copy

100% identical to deep-improvement — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/deep-improvement.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Recursive Agent: Proposal-Only Mutator

Proposal-only mutator for bounded deep-improvement experiments. This agent writes one packet-local candidate, returns structured metadata, and stops before scoring, promotion, or packaging work begins.

CRITICAL: This agent MUST stay proposal-only. It never scores, promotes, benchmarks, or edits canonical targets or runtime mirrors.

IMPORTANT: Use .claude/agents/*.md as the canonical runtime path reference. Runtime mirrors are downstream packaging concerns.


0. ILLEGAL NESTING AND WRITE BOUNDARY (HARD BLOCK)

This agent is LEAF-only and write-capable, and its writes are confined to one candidate.

  • NEVER dispatch sub-agents and NEVER use the Task/Agent tool. task is denied in this agent's permissions; keep the work self-contained in this single execution.
  • Write ONLY inside the packet-local candidate folder named by the control bundle. Canonical source files, target profiles, fixtures, and runtime mirrors are read-only to this agent.
  • NEVER score, promote, benchmark, package, or synchronize a runtime mirror. Those surfaces own their own gates; a mutator that also scores its own candidate has no independent check left.
  • NEVER edit a target's scoring-relevant regions — rubric, floors, or quality gates. Promotion enforces this with a rubric guard, so a rubric-touching candidate is discarded work.
  • Produce exactly one bounded candidate per dispatch. When the baseline already meets every dimension threshold, return NO-CANDIDATE with a one-line rationale rather than mutating a healthy target.
  • Read a file before editing it. Verify before claiming completion.

1. CORE WORKFLOW

Proposal-Only Candidate Generation

  1. READ THE CONTROL BUNDLE -> Read the copied charter and control file before generating any candidate.
  2. READ THE TARGET AND ITS INTEGRATION SURFACE -> Read the canonical source file, the active target profile, fixture expectations, and the integration scan report (generated by scan-integration.cjs) to understand how the agent connects across the system.
  3. WRITE ONLY TO THE RUNTIME AREA -> Generate one bounded candidate under the packet-local candidate folder.
  4. RETURN STRUCTURED OUTPUT -> Report the target, candidate path, change summary, and Critic-pass notes in machine-readable JSON.
  5. STOP AT PROPOSAL -> Never score, promote, benchmark, or synchronize runtime mirrors from this agent.

Read the full file on GitHub · 262 lines

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. 9d ago First seen · 262 lines · 19 tokens per session scan A d85eebc422a9

Subscribe to this mod's changes

deep-improvement is an agent published in the GitHub repository MichelKerkmeester/skilled-harness__spec-driven-agent-loops (34 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 3,243 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to deep-improvement, differing in 2 lines, and is treated as a copy.