improvement-proposer

improvement-proposer is an agent for Claude Code from Nisus74/humanise. It costs 52 tokens per session (541 once invoked), scanned A, original, MIT.

A proposal-writing agent for reviewing recorded weaknesses in the Humanise engine and suggesting narrowly scoped rule changes.

In plain words
What is it for?
Use it to turn entries in candidates.json into structured proposals covering the failure, edit location, evidence, and expected fix.
Why use it?
It keeps proposed changes tied to recorded evidence instead of relying on the conversation that produced it. This helps limit edits to the smallest relevant part of the engine.

Agent for Claude Code

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

Part of the humanise plugin — 1 skill, 7 commands, 5 agents, 2 hooks 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/nisus74/humanise/improvement-proposer
Clone the repo
git clone --depth 1 https://github.com/Nisus74/humanise

Made for: Claude Code.

Or install humanise, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 5 agents, 2 hooks.

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 improvement-proposer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nisus74/humanise/improvement-proposer.svg)](https://agentmods.dev/agents/nisus74/humanise/improvement-proposer)
Your own site
<a href="https://agentmods.dev/agents/nisus74/humanise/improvement-proposer"><img src="https://agentmods.dev/badge/agents/nisus74/humanise/improvement-proposer.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 541 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 $0.00052 $0.00541
Opus 5 $0.00026 $0.00270
Sonnet 5 $0.00010 $0.00108
Haiku 4.5 $0.00005 $0.00054

Measured 6d ago against content hash 10bb2e73ec47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

improvement-proposer 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 6d 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.

skill/agents/improvement-proposer.md · 22 lines

What it actually says

You draft rule-change proposals for the humanise engine from candidates.json, the output of evals/assertions/mine_weaknesses.py. You run in a fresh context on purpose: you argue from the recorded evidence alone, without the session that produced it.

Read evals/self-harness-loop.md first; its bounded-proposal rules are the contract. Then, for each candidate, output one proposal in the four-part schema:

  • Target: the failure, stated as behaviour ("severity-2 slop survives the sweep in investor updates"), with the cluster's count and sources.
  • Surface: the exact file and section to edit, the smallest that fixes it. One surface per proposal. Typical mappings: a dictionary-gap phrase goes in the right severity band of references/ai-slop-dictionary.md (plus a writing_checks.py list entry and a selftest fixture when the band is scripted); a recurring structural miss goes in references/structural-tells.md or a writing_checks.py threshold; a channel-specific miss goes in that channel's playbook row in references/channel-playbooks.md.
  • Evidence: the cluster itself: signature, count, representative examples from candidates.json. Never invent evidence beyond the file.
  • Expected effect: which check or behaviour changes, and what could regress (name the fixture or held-out surface that would catch it).

Also state the candidate's gate tier (it's in the file): tier 1 needs the held-in selftest green; tier 2 also needs the held-out surfaces (holdout-evals.json, the pairwise voice test) not regressed; anything touching absolute rules or the fingerprint is tier 3 and needs an adversarial read plus the user's explicit sign-off. You propose; you never apply. The orchestrator runs the gate.

For check: "voice" clusters, the right answer is usually "no safe bounded edit; the repair is corpus": say which channel needs samples and why a rule can't carry it. Forcing a mechanical rule onto a voice-level failure is how engines drift into beige compliance; don't.

Keep each proposal under 15 lines. Rank proposals by count, highest first. If two candidates share a surface, merge them into one proposal and say so.

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. 6d ago First seen · 22 lines · 52 tokens per session scan A 10bb2e73ec47

Subscribe to this mod's changes

improvement-proposer is an agent published in the GitHub repository Nisus74/humanise (1 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 541 once invoked, about $0.0003 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 agents, from other repositories

reviewer

Independent quality/craft reviewer — owns change impact, deep review, anti-slop (code + prose), and verification separation. Use when: PR review, refactor review, prose/doc review before publish, or proving blast radius before shipping.

ulises-jeremias/agent-toolkit · 51 tokens

code-reviewer

Expert code review specialist — quality/correctness/security/performance/testing with severity-ranked findings. Use when reviewer/qa-engineer delegates deep craft or PR explicitly warrants independent verification; opt-in via holistic caller.

ulises-jeremias/agent-toolkit · 45 tokens

security-reviewer

App-code security review specialist — OWASP Top 10 (injection, auth, data exposure, deps), CVE-mapped. Use when security-engineer delegates app-surface hardening or code change touches auth/data/API; opt-in via holistic caller.

ulises-jeremias/agent-toolkit · 56 tokens

Code Reviewer

Automated code review agent with security, performance, and quality analysis.

DollhouseMCP/mcp-server · 16 tokens

ios-code-reviewer

Use this agent when you need to review Swift/iOS code for quality, best practices, and potential issues. This agent should be invoked:\n\nProactive Usage Examples:\n- After implementing a new feature or component\n- After refactoring existing code\n- Before submitting a pull request\n- After making architectural…

carloshpdoc/ios-workflow-claude · 0 tokens

code-review-agent

Autonomous code review agent that analyzes code for security vulnerabilities, quality issues, and best practices adherence.

DollhouseMCP/collection · 23 tokens