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.
npx agentmods add skills/nikitacodesave/claude-code-harness/devlognpx skills add nikitaCodeSave/claude-code-harness --skill devloggit clone --depth 1 https://github.com/nikitaCodeSave/claude-code-harnessWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00114 | $0.02318 |
| Opus 5 | $0.00057 | $0.01159 |
| Sonnet 5 | $0.00023 | $0.00464 |
| Haiku 4.5 | $0.00011 | $0.00232 |
Grade A, and why
devlog 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Навык: ведение devlog
Добавляет запись в <project>/.claude/devlog/entries/ после значимых изменений. Источник правды — markdown с frontmatter; index.json + tldr.md генерируются скриптом и не редактируются вручную.
Скрипт регенерации поставляется внутри этого плагина и доступен как команда devlog-reindex на PATH, пока плагин включён (обёртка в bin/ находит skills/devlog/rebuild-index.py относительно себя — ${CLAUDE_PLUGIN_ROOT} в Bash-окружении не экспортируется, поэтому опираемся на PATH, а не на путь). Команда принимает devlog root через CLI-аргумент / $CLAUDE_PROJECT_DIR / cwd-relative fallback. Проекту достаточно создать .claude/devlog/entries/ — копировать что-либо в проект не нужно. Исключение — teammate/CI без этого плагина должны регенерировать индекс сами: тогда положи копию rebuild-index.py в <project>/.claude/devlog/rebuild-index.py, зови в README локальный путь, и при наличии project-копии используй её (она — pin проекта).
SessionStart-дайджест (тоже поставляется этим плагином). Хук hooks/session-start-digest.sh в начале каждой сессии поднимает в контекст последние 3 devlog-записи и до 3 активных progress-файлов (.claude/progress/*.md, кроме помеченных CLOSED). В проектах без .claude/devlog/ и .claude/progress/ хук молчит (exit 0 без вывода); read-only, без сети; git-статус не дублирует — его Claude Code инжектит сам. Это автоматизация session-start-ритуала harness-кита: state-on-disk сам находит следующую сессию, записи не нужно искать вручную.
Когда использовать
- После завершения фичи, исправления бага, рефакторинга
- После изменения конфигурации, API-контракта, CLI-интерфейса, auth flow
- После принятия архитектурного решения
- Когда пользователь явно просит зафиксировать изменения
НЕ использовать для:
- Опечаток, форматирования, комментариев
- Промежуточных состояний (незавершённые изменения)
- Чтения кода, research, ответов без правок
Алгоритм
1. Bootstrap devlog в проекте (один раз)
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.
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.
- 2d ago First seen · 154 lines · 114 tokens per session scan A 40e61988b4a4
devlog is a skill published in the GitHub repository nikitaCodeSave/claude-code-harness (5 stars, last pushed 3d ago), licensed MIT. It adds 114 tokens to every session and 2,318 once invoked, about $0.0006 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.