A task record system for tracking development and operations work in Feishu Base, a collaborative database and work-management service. It records work through stages such as opening, confirming, and closing a task.

Use it when accepting, confirming, completing, cancelling, or blocking coding and operations tasks. It also records who requested the work when that information is available.

It keeps accepted work auditable and makes sure tasks are properly confirmed and closed instead of disappearing from the workflow.

task-ledger — Skill for Claude Code and Codex by yunsii/wezdeck

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/yunsii/wezdeck

agentmods

npx agentmods add skills/yunsii/wezdeck/task-ledger

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yunsii/wezdeck/task-ledger/github.svg)](https://agentmods.dev/skills/yunsii/wezdeck/task-ledger)

Your own site

<a href="https://agentmods.dev/skills/yunsii/wezdeck/task-ledger"><img src="https://agentmods.dev/badge/skills/yunsii/wezdeck/task-ledger/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yunsii/wezdeck/task-ledger"><img src="https://agentmods.dev/badge/skills/yunsii/wezdeck/task-ledger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,999 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00053	$0.01999
Opus 5.5	$0.00021	$0.00800
Sonnet 5.5	$0.00011	$0.00400
Haiku 4.5	$0.00005	$0.00200

Measured 1mo ago against content hash cff69a049755, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task-ledger 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 1mo 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.

openclaw/workspace/skills/task-ledger/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development task ledger (Feishu Base)

Hard rules

Development tasks must target an allowlisted root for the active agent (see Path guard / tasks-allowlist.json). main → wezdeck|team-repo; pm → FE1 (ops). Do not hard-code another machine's /home/... in commits.
If the user asks for another repo: do not open a ledger row as accepted work; refuse and explain allowlist policy.
When accepted, time loop must close:
- open → (user confirms plan/初评/开发方式) → confirm if --confirm-required 1 → work → close
- close --status done fails if still 需确认 and never confirmed
- cancelled / blocked / failed may close without confirm
Never write secrets into the ledger.
Final reply must include task_id.
If CLI fails, say so; do not invent task_id.
When the request has a clear 需求提出人 (product / user who asked): record them on open/update with --requester-id <ou_…> (preferred). Feishu person field name: 需求提出人. Do not leave it blank when known.
Order with worktree: open first; after claw worktree exists, update cwd/分支; after user confirms 初评+开发方式, confirm; then implement.
Pure Q&A: do not open a row. As soon as the user accepts implementation, open before assess/create (same turn is OK if open is first).
Test hygiene: after every smoke / CLI self-test that opens a row, delete that row (and local index entry). Do not leave smoke / time-loop / *-test rows in the production Base table. Soft close is not enough for pure tests — use hard delete.

Path guard

Config file (authoritative): ~/.openclaw/tasks-allowlist.json (from openclaw/config/tasks-allowlist.json.example).
Resolver: openclaw/scripts/tasks-allowlist.py (show / check / roots).
Agent: OPENCLAW_TASKS_AGENT or default main (paths come from config, not env).
CLI allowlists local --cwd / path-form --repo only (not remote URLs).
Base field 仓库 = https web URL (clickable in Feishu); cwd = local path. CLI rewrites git@… / ssh://… / ….git → https://host/org/repo.

Read the full file on GitHub · 146 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.

1mo ago Changed cff69a049755
1mo ago First seen · 146 lines · 53 tokens per session scan A 2de85021d824

Subscribe to this mod's changes

task-ledger is a skill published in the GitHub repository yunsii/wezdeck (4 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 1,999 once invoked, about $0.0002 per session on Opus 5.5. 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.

Claude Code Project management agent-orchestration ai-agents codex developer-tools git-worktree

paperclip

Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.

paperclipai/paperclip · 54 tokens

task-ledger

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Development task ledger (Feishu Base)

Hard rules

Path guard

What this file has done since we first saw it

Other skills, from other repositories

paperclip

paperclip-task-bridge

gh-file-issue

gh-treasure-hunt

issue-triage

review-my-team