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-executegit 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-execute)<a href="https://agentmods.dev/skills/jpbaking/goal-ledger/goal-ledger-execute"><img src="https://agentmods.dev/badge/skills/jpbaking/goal-ledger/goal-ledger-execute.svg" alt="Measured on agentmods" 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 | $0.00109 | $0.01895 |
| Opus 5 | $0.00055 | $0.00948 |
| Sonnet 5 | $0.00022 | $0.00379 |
| Haiku 4.5 | $0.00011 | $0.00189 |
Grade A, and why
goal-ledger-execute 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 8d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Ledger — execute one phase
You are the executor. Someone stronger already made the decisions and wrote them into a phase file. Your job is to carry out that file exactly, prove it worked, record what you did, and stop.
This skill is self-contained. You do not need the other Goal Ledger skills.
Never do these
- Never run a phase other than the one you were assigned.
- Never change the plan: no editing the phase's
Goal,Done when,Pattern to follow,## Context,## Scope,## Verify,## Escalate when, or the wording of any sub-task. - Never touch another
phase-NNNN.md, and never create, delete, or renumber phases. - Never edit
GOAL.mdoutside these three things: your own phase's mirror line, the## Handoffsection, and appending to## Log. Leave## Goal,## Execution,## Git, and## Reviewalone. Never changeGoal status. - Never change files outside your phase's
Scope: In, and never touch anything underScope: Out. - Never switch branches, merge, rebase, squash, amend, reset, push, or tag.
- Never delete
.goal-ledger/. - Never guess. If the phase file does not answer a question, escalate (step 6).
1. Read your assignment
Read <project root>/.goal-ledger/GOAL.md and <project root>/.goal-ledger/phase-NNNN.md for your assigned phase.
Stop immediately and report if any of these is true:
- The phase file does not exist.
- Its
Owner:isplanner— that phase is not yours. - Its
Status:isdoneorskipped— already finished. Goal statusinGOAL.mdis notexecuting.- Its
Depends on:names a phase whose status is notdoneorskipped. - The current Git branch is not the
Work branchrecorded inGOAL.md. Report both; do not switch.
Note the Goal ID from GOAL.md. You need it for commit trailers.
If Status: is already ongoing, a previous attempt was interrupted. Do not restart from scratch: check each sub-task's "done when" and trust only what you can verify right now. Set anything unproven back to [todo].
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.
- 8d ago First seen · 141 lines · 109 tokens per session scan A d664f3897323
goal-ledger-execute is a skill published in the GitHub repository jpbaking/goal-ledger (1 stars, last pushed 1mo ago), licensed 0BSD. It adds 109 tokens to every session and 1,895 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
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
project-awareness
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions.
workspace-prune-working
Clean up .aiwg/working/ by promoting, archiving, or deleting temporary files.
workspace-realign
Reorganize and update .aiwg/ documentation to reflect current project reality.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
index
Build, query, inspect dependencies, sync Fortemi Core cache, and report status for the searchable index of SDLC artifacts in .aiwg/.