goal-ledger-resume

goal-ledger-resume is a skill for Claude Code, Codex from jpbaking/goal-ledger. It costs 113 tokens per session (1,322 once invoked), scanned A, original, 0BSD.

A recovery guide for an unfinished Goal Ledger, a record of a coding task's plan, progress, and verified changes. It uses the ledger and Git history to determine what another agent completed before an interruption.

In plain words
What is it for?
Use it to resume interrupted agent tasks, reconcile progress with Git, verify what was completed, and continue from the first safe unfinished step.
Why use it?
It helps prevent lost work or duplicated work after a crash, hand-off, or loss of conversation context. It checks the recorded branch, commits, starting points, and uncommitted files before continuing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

Good fit Use it to resume interrupted agent tasks, reconcile progress with Git, verify what was completed, and continue from the first safe unfinished step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jpbaking/goal-ledger/goal-ledger-resume
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.

Any agent
npx skills add jpbaking/goal-ledger --skill goal-ledger-resume
Clone the repo
git clone --depth 1 https://github.com/jpbaking/goal-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.

agentmods badge for goal-ledger-resume

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpbaking/goal-ledger/goal-ledger-resume/github.svg)](https://agentmods.dev/skills/jpbaking/goal-ledger/goal-ledger-resume)
Your own site
<a href="https://agentmods.dev/skills/jpbaking/goal-ledger/goal-ledger-resume"><img src="https://agentmods.dev/badge/skills/jpbaking/goal-ledger/goal-ledger-resume/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.

agentmods 80×15 button for goal-ledger-resume

Your own site · 80×15
<a href="https://agentmods.dev/skills/jpbaking/goal-ledger/goal-ledger-resume"><img src="https://agentmods.dev/badge/skills/jpbaking/goal-ledger/goal-ledger-resume.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,322 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00113 $0.01322
Opus 5 $0.00056 $0.00661
Sonnet 5 $0.00023 $0.00264
Haiku 4.5 $0.00011 $0.00132

Measured 11d ago against content hash 83b8135aba43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

goal-ledger-resume 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 11d 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.

.agents/skills/goal-ledger-resume/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal Ledger — resume and recover

Treat the ledger and Git as evidence left by another agent — possibly a weaker one, possibly mid-sentence. Establish what is verified, repair bookkeeping without discarding work, and continue from the first safe action.

1. Establish your role

  • If you were handed a specific phase to run, use the goal-ledger-execute skill instead.
  • If you are an ordinary helper subagent working from a delegated prompt, ignore the ledger and this skill and continue only the task you were given. An unfinished ledger is not a blocker for that task and is not worth reporting unless the prompt asks for ledger work.
  • Otherwise you are resuming as the planner: you own the goal, the plan, Goal status, Git, and Gate D.

Read sections 1–4 of the sibling goal-ledger skill. If .goal-ledger/GOAL.md is missing, say there is no ledger to resume. If status is completed or abandoned, report that and stop.

2. Decide whether this request resumes the goal

  • The user asks to resume, or the request matches the recorded Outcome: resume without another intent question.
  • The ledger is blocked-on-human and the user answers its blockers: record the answers into the affected phase's ## Context so a re-delegated executor can see them, return affected items to [todo], and continue.
  • Status drafting: return to Gate A. Status approved: if strategy, branch, baseline, or approval commit is missing or inconsistent, return to Gate B; otherwise return to Gate C.
  • Status in-review: Gate D was started and not finished. Re-run it from the top rather than trusting a partial ## Review.
  • Status awaiting-acceptance: report the result and ask for acceptance; do not resume execution.
  • An unrelated request: report the unfinished goal and ask whether to resume it or use the goal-ledger-abandon skill. Never overwrite it silently.

3. Reconcile Git

Skip Git steps when Repository: no.

  1. Verify the current branch equals Work branch. If not, do not switch with a dirty tree. Report both branches and ask before switching.
  2. Verify the immutable baseline exists and is an ancestor of HEAD. If not, stop with the exact inconsistency.
  3. Inspect git log <baseline>..HEAD, including commit trailers. Classify matching Goal-ID commits, foreign commits, merge commits, and phase begin/close pairs. Record foreign history in Handoff; it may prohibit squashing but does not justify deleting work.
  4. Compare locally known starting/work upstream refs with their recorded Gate B SHAs. Record advances, rewinds, divergence, or goal-commit publication in Handoff. On current-branch, any upstream movement prohibits automated squash.
  5. Inspect the worktree. A phase-begin commit followed by a clean tree means phase work did not start. A dirty tree means work may have stopped mid-phase; inspect the diff and do not discard it.
  6. A completed phase without a matching close commit is unverified until its ## Verify passes. A close commit with stale ledger status may be reconciled after its check passes.

Read the full file on GitHub · 63 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. 11d ago First seen · 63 lines · 113 tokens per session scan A 83b8135aba43

Subscribe to this mod's changes

goal-ledger-resume is a skill published in the GitHub repository jpbaking/goal-ledger (1 stars, last pushed 1mo ago), licensed 0BSD. It adds 113 tokens to every session and 1,322 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.