improve

improve is a skill for Claude Code, Codex from tpierrain/kenjaku. It costs 31 tokens per session (460 once invoked), scanned A, original, Apache-2.0.

A continuous-improvement workflow for a coding or automation harness: the surrounding files and processes that help agents work.

In plain words
What is it for?
Use it to inspect the improvement backlog, identify problems from a session, propose priorities, and implement and test selected changes.
Why use it?
It turns repeated workarounds, failed skills, and hard-to-find information into tracked improvement tasks instead of letting the same friction recur.

Skill for Claude CodeCodex

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/tpierrain/kenjaku/improve
Any agent
npx skills add tpierrain/kenjaku --skill improve
Clone the repo
git clone --depth 1 https://github.com/tpierrain/kenjaku

Made for: Claude Code, Codex.

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 improve

README.md
[![agentmods](https://agentmods.dev/badge/skills/tpierrain/kenjaku/improve.svg)](https://agentmods.dev/skills/tpierrain/kenjaku/improve)
Your own site
<a href="https://agentmods.dev/skills/tpierrain/kenjaku/improve"><img src="https://agentmods.dev/badge/skills/tpierrain/kenjaku/improve.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 460 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 $0.00031 $0.00460
Opus 5 $0.00015 $0.00230
Sonnet 5 $0.00006 $0.00092
Haiku 4.5 $0.00003 $0.00046

Measured 4d ago against content hash ef77fafb86f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

improve 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 4d 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.

.claude/skills/improve/SKILL.md · 48 lines

What it actually says

/improve — Continuous improvement of the harness

Routing

  • No argumentSession mode (A).
  • ajouter <description> (or add) → Quick-add mode (B).

MODE A — Improvement session

A1 — Read the backlog and observe

  1. Read vault/backlog/harnais.md (backlog of pending improvements).
  2. Read the most recently modified files in .claude/skills/ to understand the state of the harness.
  3. If the conversation has 10+ exchanges, detect frictions:
    • Repeated workarounds (same action 2+ times)
    • Questions the vault couldn't answer
    • Failed skills or unsatisfactory results
    • Too many rounds to find a piece of information Add the observations to the backlog with the [observation] tag.

A2 — Propose the priority improvements

Present the 3 most impactful improvements, prioritized by impact/effort ratio, recurrence, leverage. For each: title + tag, impact (1 sentence), effort (quick win < 30 min / project), proposal (2-3 lines). End with: "Which one do we tackle?"

A3 — Implement

  1. Make the changes (skills, CLAUDE.md, vault structure…).
  2. Test if possible (dry run, syntax check).
  3. Mark the item [x] + date in vault/backlog/harnais.md.
  4. Let the hook commit.

MODE B — Quick add

Add the idea to vault/backlog/harnais.md: categorize (quick win / project / idea), [explicite] tag + today's date, confirm in one line. Do not implement.


Passive observation (outside the skill)

Rule in CLAUDE.md (section 5). Applies automatically to every session of 10+ exchanges, not only when /improve is invoked.

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. 4d ago First seen · 48 lines · 31 tokens per session scan A ef77fafb86f1

Subscribe to this mod's changes

improve is a skill published in the GitHub repository tpierrain/kenjaku (80 stars, last pushed 10d ago), licensed Apache-2.0. It adds 31 tokens to every session and 460 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 2026-08-30.

Related

Other skills, from other repositories

lint

Run the LLM Wiki health check: orphans, broken links, contradictions, stale pages, index sync, MOC coverage, frontmatter fields, Exploration Gate, v5 verification fields, Bias Check, cross-vault links, and Core Context freshness; also responds to /lint and 위키 점검.

johnfkoo951/cmds-llm-wiki · 64 tokens

refresh-context

Re-snapshot Core Context.md from the 9 mothership system files and key essays when the mothership changes or the snapshot is older than 30 days; also responds to /refresh-context and 코어 컨텍스트 갱신.

johnfkoo951/cmds-llm-wiki · 51 tokens

status

Show the LLM Wiki state at a glance: counts, recent activity, index drift, inbox backlog, collectionPurpose/mainVault/explored/verificationStatus coverage, and Core Context snapshot age; also responds to /status and 상태 점검.

johnfkoo951/cmds-llm-wiki · 51 tokens

capture-tabs

Capture Chrome tab groups, browser research bundles, or ChatGPT/Gemini/Grok/Claude/Perplexity sessions into LLM Wiki Inbox markdown; also responds to 탭 캡처, 리서치 캡처, Deep Research 캡처, and /capture-tabs.

johnfkoo951/cmds-llm-wiki · 61 tokens

ingest

Ingest a URL, file, raw text, or Inbox item into the LLM Wiki with the purpose gate, mothership link search, raw-source preservation, Wiki compilation, index/log update, and review; also responds to /ingest and 인제스트.

johnfkoo951/cmds-llm-wiki · 56 tokens

reindex

Manually re-run qmd indexing and embeddings for wiki, rawsources, and queries after Obsidian edits, bulk moves, or embedding-model changes; also responds to /reindex and 재색인.

johnfkoo951/cmds-llm-wiki · 45 tokens