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 skills add jpbaking/goal-ledger --skill goal-ledger-abandongit clone --depth 1 https://github.com/jpbaking/goal-ledgerWrote 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.
[](https://agentmods.dev/skills/jpbaking/goal-ledger/goal-ledger-abandon)<a href="https://agentmods.dev/skills/jpbaking/goal-ledger/goal-ledger-abandon"><img src="https://agentmods.dev/badge/skills/jpbaking/goal-ledger/goal-ledger-abandon/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.
<a href="https://agentmods.dev/skills/jpbaking/goal-ledger/goal-ledger-abandon"><img src="https://agentmods.dev/badge/skills/jpbaking/goal-ledger/goal-ledger-abandon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00070 | $0.00764 |
| Opus 5 | $0.00035 | $0.00382 |
| Sonnet 5 | $0.00014 | $0.00153 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
goal-ledger-abandon 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 10d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Ledger — abandon without erasing history
Abandonment is a durable terminal state, not deletion. Preserve the ledger and work so the decision can be understood or reversed later.
Abandonment is planner-only. If you were handed a single phase to execute, you cannot abandon the goal: set that phase to needs-human — reason: and stop.
1. Load and summarize
Read sections 1–4 of the sibling goal-ledger skill. If there is no ledger, say so and stop. If status is already completed or abandoned, report it and stop.
Show the Goal ID, Outcome, strategy and work branch, phase counts, blockers, matching goal commits, and dirty worktree state. Explain that abandonment will keep the ledger, commits, and code changes.
If a phase is ongoing, an executor may still be holding it. Say so and confirm that work has actually stopped before abandoning.
2. Confirm abandonment
Ask explicitly: "Mark this goal abandoned while preserving its ledger and work?" Anything short of a clear yes changes nothing.
On confirmation:
- Set Goal status
abandoned. - Update Handoff: current position
abandoned, next actionnone, and blockers with the user's reason when provided. - Append an abandonment log entry. Do not change phase statuses merely to make them terminal.
- Run the validator bundled with the sibling
goal-ledgerskill asscripts/validate_goal_ledger.py --root <project root>. Repair ledger-format errors before preserving the state; warnings do not prevent abandonment. If Python 3 is unavailable, check the format manually.
3. Preserve Git state
When Repository: yes:
- If Git preparation never completed (
Strategy: none, missing baseline, or no approval commit), do not create or switch branches merely to abandon a draft. Save the abandoned ledger locally; commit it only if the user separately asks to record it on the current branch. - After Git preparation, if the worktree contains partial goal work, ask separately whether to checkpoint those goal-owned changes in the abandonment commit. Default No. Never stage unrelated files.
- After Git preparation, whether or not partial code is included, stage
.goal-ledger/GOAL.mdand creategoal-ledger(abandon): <title>with the matching Goal ID trailer. If partial work is not included, leave it untouched and report it as uncommitted. - Never reset, revert, delete the work branch, or rewrite history.
- For an isolated branch with a clean tree, offer to switch back to
Starting branch; require explicit permission and keep the goal branch intact. - If partial work remains dirty because checkpointing was declined, stay on the goal branch. Offer a separately authorized checkpoint or recoverable stash, or leave it in place; never carry it onto the starting branch or discard it automatically.
- On
current-branch, remain on that branch and warn that goal commits are part of its history.
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.
- 10d ago First seen · 53 lines · 70 tokens per session scan A b47bda1e7d3c
goal-ledger-abandon is a skill published in the GitHub repository jpbaking/goal-ledger (1 stars, last pushed 1mo ago), licensed 0BSD. It adds 70 tokens to every session and 764 once invoked, about $0.0003 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
mulmoterminal-dirs
Colour-code and order the directories you actually work in, from wherever you are. Writes each project's /.mulmoterminal.json — name badge, project icon image, the seven chrome colours, xterm palette (theme / colors), terminal font size, orderPriority (where it sits in the grid and in the launcher's chips), and…
mulmoterminal-keys
Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
nl-router
Route natural language requests to appropriate skills and workflows by parsing intent and matching trigger patterns.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.
summarize-transcript
Analyze and summarize a transcript, meeting notes, or discussion thread into a clear actionable document.