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/littlecabbage/worklog-skill/worklognpx skills add littlecabbage/worklog-skill --skill workloggit clone --depth 1 https://github.com/littlecabbage/worklog-skillWhat 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 | $0.00081 | $0.02385 |
| Opus 5 | $0.00041 | $0.01192 |
| Sonnet 5 | $0.00016 | $0.00477 |
| Haiku 4.5 | $0.00008 | $0.00238 |
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.
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`). 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
- Infer the mode from current context before asking the user to fill fields.
- 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.envor 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.
- 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.
- 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
summaryand the body's leading sections) - 0-2 experience candidates marked as pending
- inferred
- Ask only one question by default: "Save this draft, edit mode/title/tags, or discard it?"
- Write the session log to
<project-root>/.worklog/YYYY-MM-DD/<task-slug>.mdonly after confirmation. Do not invokefinish_worklog.pybefore the user confirms — confirmation is a workflow obligation, not a stored flag.mode_confidence/mode_evidenceare shown in the UI but not persisted. - After a successful save, archive the capture draft by moving
.worklog/draft/<current_session_id>/to.worklog/draft/.archived/<current_session_id>/. - Update
INDEX.mdin newest-first order. - Promote reusable findings into
EXPERIENCES.mdandindex.jsononly when the user explicitly confirms the experience candidates. - Search
index.jsonwithjqbefore reading older markdown in full.
What ships with it
21 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.
- assets/templates/debug-session.md 539 B
- assets/templates/dev.md 645 B
- assets/templates/experiences.md 933 B
- assets/templates/index.json 2.4 KB
- assets/templates/index.md 475 B
- assets/templates/mixed.md 664 B
- assets/templates/read.md 506 B
- references/worklog-format.md 6.7 KB
- references/worklog-format.zh.md 6.5 KB
- scripts/capture_hook.py 4.2 KB runs code
- scripts/deprecate_experience.py 1.3 KB runs code
- scripts/finish_worklog.py 3.6 KB runs code
- scripts/hooks_install.py 8.6 KB runs code
- scripts/init_worklog.py 5.7 KB runs code
- scripts/reindex_worklog.py 616 B runs code
- scripts/search_worklog.py 1.5 KB runs code
- scripts/worklog_lib.py 37 KB runs code
- tests/test_body_payload.py 11 KB runs code
- tests/test_capture_hook.py 6.4 KB runs code
- tests/test_install.py 9.9 KB runs code
- tests/test_language.py 5.9 KB runs code
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 · 119 lines · 81 tokens per session scan C e3881f7c4cd1
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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…
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.
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.