klimkit-implement

A full workflow guide for substantial software changes, from understanding the request through implementation, checking, reflection, and final review.

In plain words
What is it for?
Use it when implementing, fixing, refactoring, releasing, migrating, connecting, or completing a non-trivial repository task.
Why use it?
It gives coding agents a repeatable process for handling code, documentation, releases, configuration, interfaces, backend work, and security-sensitive changes.

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/klimentij/klimkit/klimkit-implement
Any agent
npx skills add klimentij/klimkit --skill klimkit-implement
Clone the repo
git clone --depth 1 https://github.com/klimentij/klimkit

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 975 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 $0.00074 $0.00975
Opus 5 $0.00037 $0.00487
Sonnet 5 $0.00015 $0.00195
Haiku 4.5 $0.00007 $0.00097

Measured 3d ago against content hash e45effe009c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

klimkit-implement 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.

skills/klimkit-implement/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Klimkit Implement

Use this as the skills-first replacement for the old global AGENTS.md implementation workflow. Keep the work in the main agent by default. Do not use subagents for exploration, checklists, debugging, security, or reflection unless the user explicitly asks; the only built-in subagent use is the final-review gate.

Defaults

  • Treat Klimkit as a Vercel Skills CLI package first: install and update the root skills/ library with npx skills.
  • Use normal Codex app or CLI sessions plus installed Klimkit skills for day-to-day work.
  • Keep task evidence in the project repository, not in generated home files.
  • Treat older Klimkit runtime machinery as deprecated legacy material. Do not route new workflows through it unless the user explicitly asks to maintain legacy code.

Workflow

  1. Intake
    • Read the latest user request, repo instructions (AGENTS.md), relevant docs/work/ LOGs (descend selectively), docs, and nearby code.
    • If the repo lacks the docs/work/ layout, use klimkit-setup.
    • Decide whether the work is implementation, debugging, release, review, research, UI/proof, or security-sensitive.
  2. Explore
    • Use klimkit-code-explorer inline when the code path is unfamiliar, broad, or risky.
    • Use direct repo reads for simple tasks.
  3. Checklist
    • Use klimkit-checklister before code changes for implementation work.
    • Treat the checklist as blocking unless the user changes scope.
  4. Implement
    • Choose the narrow method skill when helpful: klimkit-diagnose, klimkit-tdd, klimkit-walkthrough, klimkit-report-server, or klimkit-create-worktree.
    • Keep edits surgical and aligned with existing repo style.
    • Do not route new work through deprecated runtime, Switchboard, sync scripts, or plugin machinery unless explicitly maintaining legacy code.
    • If a task asks to migrate old Klimkit runtime behavior into skills, make the target skill own any reference scripts, templates, and setup instructions it needs.
  5. Verify
    • Run checks that match the checklist and blast radius.
    • Record exact commands, important outputs, skipped checks, and remaining risk.
    • For UI/proof work, produce inspectable report evidence when the repo workflow requires it.
  6. Security
    • Use klimkit-security-auditor before completion when the change touches auth, secrets, permissions, containers, network exposure, infrastructure, user data, or unsafe defaults.
  7. Reflect
    • Use klimkit-reflector after verification and before final review for non-trivial work.
    • If reflection exposes a material gap, fix it and rerun impacted checks.
  8. Final Review
    • Draft the exact final response.
    • Run fresh final-review passes with klimkit-final-reviewer.
    • Prefer 3 independent final-review subagents when subagents are available and the user has not forbidden them. Give each only the original request, checklist, changed files, verification evidence, reflection note, proof artifacts, and exact draft response.
    • If subagents are unavailable or forbidden, run klimkit-final-reviewer inline and state that limitation.
    • Do not claim completion until final review returns READY FOR USER or all remaining gaps are explicitly reported.
  9. Report
    • Tell the user what changed, what passed, what was skipped, and how to inspect the result.
    • For commits on main in this repo, create or update the latest GitHub release according to repo instructions.

Read the full file on GitHub · 62 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 62 lines · 74 tokens per session scan A e45effe009c0

Subscribe to this mod's changes

klimkit-implement is a skill published in the GitHub repository klimentij/klimkit (7 stars, last pushed 23d ago), licensed MIT. It adds 74 tokens to every session and 975 once invoked, about $0.0004 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

happiness-skill

当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.

kangarooking/cangjie-skill · 136 tokens

agr-cli

Install, share, sync, and create AI agent skills across coding tools (Claude Code, Cursor, Codex, OpenCode, Copilot, Pi) using the agr CLI. Use whenever the user mentions agr, agr.toml, agr.lock, agrx, or asks to: add a skill ("install the pdf skill", "agr add ..."), sync agent resources across tools, share skills…

computerlovetech/agr · 147 tokens

agr-release

Release process for the agr package. Handles version bumping (major/minor/patch/beta), changelog updates, pre-release quality checks, git tagging, and monitoring the GitHub Actions publish pipeline. Use this skill whenever the user wants to cut a release, bump the version, publish to PyPI, or asks about the release…

computerlovetech/agr · 91 tokens

hook-craft

Specializes in chapter openings (hooks) and chapter endings (pulls). Every chapter must start with a reason to keep reading and end with a reason to turn the page. Runs after prose-craft, before chaos-engine. The skill that prevents the reader from putting the book down.

felipelobomotta-blip/book-genesis-v4 · 61 tokens

kafka-topic-audit

Audit all Kafka topic configurations against production best practices using the Lenses MCP server. Checks replication factor, retention, partitions, compaction, naming conventions, orphaned topics and missing metadata. Use when user says "audit my topics", "check topic configs", "topic health check" or asks about…

lensesio/agentic-engineering-for-apache-kafka · 83 tokens

book-genesis

Use when the user wants to create, plan, draft, evaluate, revise, package, or run a complete AI-assisted book pipeline. Book Genesis turns a one-line idea into a book project with intake, foundation, architecture, drafting, adversarial audit, Genesis Score, and editorial package artifacts.

felipelobomotta-blip/book-genesis-v4 · 63 tokens