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-statusgit 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-status)<a href="https://agentmods.dev/skills/jpbaking/goal-ledger/goal-ledger-status"><img src="https://agentmods.dev/badge/skills/jpbaking/goal-ledger/goal-ledger-status/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-status"><img src="https://agentmods.dev/badge/skills/jpbaking/goal-ledger/goal-ledger-status.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 | $0.00106 | $0.00662 |
| Opus 5 | $0.00053 | $0.00331 |
| Sonnet 5 | $0.00021 | $0.00132 |
| Haiku 4.5 | $0.00011 | $0.00066 |
Grade A, and why
goal-ledger-status 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 12d 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.
What it actually says
Goal Ledger — status and handoff report
This skill is strictly read-only: no status changes, log entries, commits, repairs, branch switches, or cleanup.
Read sections 1–4 of the sibling goal-ledger skill. If .goal-ledger/GOAL.md is absent, say there is no Goal Ledger and stop.
Read GOAL.md and every phase file. When Repository: yes, read the current branch, worktree status, and git log <baseline>..HEAD with trailers. Report:
Run the validator bundled with the sibling goal-ledger skill in read-only mode as scripts/validate_goal_ledger.py --root <project root>. Include its errors and warnings in the report. If Python 3 is unavailable, perform the same read-only checks manually.
Goal: <title> — <goal status>
Goal ID: <id>
Outcome: <outcome>
Mode: <solo | delegated>; planner <tier>; executor <tier>
Strategy: <strategy>; start <starting branch>; work <work branch>
Baseline: <short SHA>
Upstreams at start: start <value>; work <value> (omit without Git)
Phases: <X> done, <Y> skipped, <Z> needs-human, <W> todo, <V> ongoing
Per phase:
- phase-NNNN <status> — <title> (owner: <owner>, <a>/<b> sub-tasks done)
Handoff: <current position>; next <next role> — <next action>
Review: reviewed by <value>; verification <value>; findings <value>
Goal commits: <N>; tree <clean | DIRTY — possible interrupted work> (omit without Git)
Needs you:
- <exact blocker> (omit if none)
Warnings:
- <branch mismatch / baseline problem / upstream movement / foreign or merge commit / phase state mismatch / begin without close / published history / done phase with no evidence> (omit if none)
When the next action is a delegation, also state which phase is ready and whether its file is executor-ready: exact paths in Scope: In, a runnable ## Verify, and no sub-task that still requires a decision. Report gaps as warnings — do not fix them here.
End with one recommendation: delegate the next phase, resume with the
goal-ledger-resume skill, run Gate D, review for acceptance, keep the
completed record, or use the goal-ledger-abandon skill if the user
explicitly wants to stop.
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.
- 12d ago First seen · 49 lines · 106 tokens per session scan A e00240c686cd
goal-ledger-status is a skill published in the GitHub repository jpbaking/goal-ledger (1 stars, last pushed 1mo ago), licensed 0BSD. It adds 106 tokens to every session and 662 once invoked, about $0.0005 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
aiwg-pr
AIWG-specific pull request delivery workflow for AIWG product/workspace changes; not the generic repository PR process.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
commit-and-push
Create a well-formatted git commit and push to remote repository.
steward-prep-delivery
Steward-assisted prep for filing issues and PRs — environment capture, template selection, duplicate detection, delivery-policy compliance check.
contribute-start
Initialize an AIWG contribution workflow by creating a feature branch, configuring DCO, and linking a tracking issue.
customize-contribute-back
Contribute a user's AIWG customization back upstream as a PR — reviews for general applicability, creates branch, opens PR.