Borrowing it
Nothing to install: this file belongs to IgorGanapolsky/ThumbGate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/IgorGanapolsky/ThumbGate/main/.claude/skills/task-state-ledger/SKILL.mdgit clone --depth 1 https://github.com/IgorGanapolsky/ThumbGateWrote 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/igorganapolsky/thumbgate/task-state-ledger)<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/task-state-ledger"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/task-state-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.
<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/task-state-ledger"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/task-state-ledger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 16 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00097 | $0.00974 |
| Opus 5 | $0.00048 | $0.00487 |
| Sonnet 5 | $0.00019 | $0.00195 |
| Haiku 4.5 | $0.00010 | $0.00097 |
Grade A, and why
task-state-ledger scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
notice yourself re-deriving "where am I" with repeated gh/git/curl dumps, when a How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task State Ledger — Stop Getting Lost
The failure this prevents
You re-derive state every turn (where's the PR, what's on main, what's deployed)
with expensive gh/git/curl dumps. The dumps flood context, bury the signal,
and you lose the thread. This is the "constantly stuck and lost" failure. The fix
is mechanical: write state down once, update it as you go, read it instead of
re-deriving it. (Anthropic context-engineering: external structured note-taking
is one of the three core long-horizon techniques, alongside compaction and
sub-agents — see https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents)
The rule
For any task with 3+ steps or that crosses a turn, the FIRST action is to create
or open a ledger at .thumbgate/implementation-notes.md or a task-specific
gitignored .thumbgate/implementation-notes/<date>-<task>.md. Do not write
operator scratchpads under tracked .claude/implementation-notes/; those are
private working notes, not product documentation. The ledger is the single
source of truth.
Ledger format (keep it short — it's a dashboard, not a diary)
# <task> — <date>
## Goal (one sentence)
<the actual end state that means "done">
## Current step
<the ONE thing in flight right now>
## State (verified facts only — each with how/when verified)
- main HEAD: <sha> (git rev-parse origin/main @ HH:MM)
- deployed buildSha: <sha> (curl /health @ HH:MM)
- PR #NNNN: <state>/<mergeState> (gh pr view @ HH:MM)
## Steps (sequential — one in_progress at a time)
- [x] step that's done — evidence
- [ ] step in flight ← YOU ARE HERE
- [ ] next step
- [ ] ...
## Decisions & corrections
- <decision> because <why> (mark VERIFIED / UNVERIFIED)
- WRONG: <thing I claimed that was false> → corrected to <truth> @ HH:MM
## Blockers / open questions for the CEO
- <thing only the user can unblock>
Protocol
- Open the ledger before doing anything else on a multi-step task. If it exists, read it instead of re-deriving state.
- Update "Current step" + "State" after each verification, not at the end. When you run the verifying command, write its result + timestamp into the ledger.
- One step
in_progressat a time. If you're tempted to start a second, stop — see thescope-disciplineskill. - Log corrections inline. When "are you sure?" reveals you were wrong, write the WRONG→corrected line. This stops you re-making the same wrong claim.
- Read the ledger at the start of every turn on a continuing task. That is how you stop being "lost": the answer to "where am I" is a file read, not 10 tool calls.
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.
- 9d ago First seen · 90 lines · 97 tokens per session scan A 1a254c55dae0
task-state-ledger is a skill published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 974 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
forge-quench
Systematically reduce .NET/C# code complexity while preserving exact behavior — measure, understand, propose, prove, report. Use after a feature is complete and tests pass, when code works but is harder to maintain than it should be.
onboarding
Walk a new developer through .NET project setup, architecture, key files, and first task. Use when someone new joins the team or needs to understand the codebase.
test-sweep
Run all test suites (unit, integration, API, E2E) and aggregate results into a summary report. Use after completing execution slices or before the Review Gate.
agentguard
Runtime guardrails for AI coding agents. Stop loops, budget overruns, retry storms, and timeouts before they burn money. Zero dependencies, local-first, MIT licensed.
sodam-loop-undo
A restore tool for undoing a mistaken change by returning to the backup made before the previous task started. Its aliases mean “undo” and “restore” in Korean.
slides
A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.