worklog

A worklog tool for saving and retrieving records of coding sessions, source-reading sessions, debugging sessions, and mixed development work.

In plain words
What is it for?
Use it to draft session summaries, preserve decisions and progress, and reuse experiences in later work on the project.
Why use it?
It gathers session events, file history, task records, Git information, and conversation context so a worklog reflects what actually happened.

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

Made for: Claude Code, Codex.

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,385 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00081 $0.02385
Opus 5 $0.00041 $0.01192
Sonnet 5 $0.00016 $0.00477
Haiku 4.5 $0.00008 $0.00238

Measured 2d ago against content hash e3881f7c4cd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

worklog scanned grade C with 1 finding 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.

The scan reads SKILL.md. This mod also ships 12 executable files (scripts/capture_hook.py, scripts/deprecate_experience.py, scripts/finish_worklog.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- Sensitive paths are redacted at capture time (`.env*`, `*secret*`, `*credential*`, `*token*`, `*.pem`, `*.key`, `id_rsa*`, anything under `.ssh/` or `.aws/`, `.netrc`).
worklog/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Worklog

Default workflow: context-first, draft-first

  1. Infer the mode from current context before asking the user to fill fields.
  2. Cross-reference active capture sources first (when enabled). Before drafting from memory, check these five sources in order and use them as the timeline backbone:
    • .worklog/draft/<current_session_id>/events.jsonl — structured events captured by the hook layer (user prompts, tool calls, stops). Trust this over recall when they disagree.
    • ~/.claude/file-history/<current_session_id>/ — pre/post snapshots of files Claude edited; still apply redaction since these may contain .env or secrets if such files were edited.
    • ~/.claude/todos/<current_session_id>-agent-*.json — task progress recorded during the session.
    • git status / git diff --stat / git log <session-start>..HEAD — repo-side evidence.
    • The current conversation context — for goals, decisions, and rationale that did not leave a file trail. When sources disagree, prefer events and git evidence over recall. When ambiguity remains, ask the user one targeted question rather than guessing.
  3. Draft a save-ready worklog from the cross-referenced evidence above plus the conversation, workspace, git state, changed files, commands run, errors, decisions, and verification results that are visible to you.
  4. Show one compact confirmation containing:
    • inferred mode, mode_confidence, and 2-5 evidence bullets
    • generated title, status, tags, and duration if available
    • 3-6 session summary bullets (these become the summary and the body's leading sections)
    • 0-2 experience candidates marked as pending
  5. Ask only one question by default: "Save this draft, edit mode/title/tags, or discard it?"
  6. Write the session log to <project-root>/.worklog/YYYY-MM-DD/<task-slug>.md only after confirmation. Do not invoke finish_worklog.py before the user confirms — confirmation is a workflow obligation, not a stored flag. mode_confidence / mode_evidence are shown in the UI but not persisted.
  7. After a successful save, archive the capture draft by moving .worklog/draft/<current_session_id>/ to .worklog/draft/.archived/<current_session_id>/.
  8. Update INDEX.md in newest-first order.
  9. Promote reusable findings into EXPERIENCES.md and index.json only when the user explicitly confirms the experience candidates.
  10. Search index.json with jq before reading older markdown in full.

Read the full file on GitHub · 119 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. 2d ago First seen · 119 lines · 81 tokens per session scan C e3881f7c4cd1

Subscribe to this mod's changes

worklog is a skill published in the GitHub repository littlecabbage/worklog-skill (11 stars, last pushed 3mo ago), licensed MIT. It adds 81 tokens to every session and 2,385 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens