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 gviiisen/repo-context-ledger --skill repo-context-ledgergit clone --depth 1 https://github.com/gviiisen/repo-context-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/gviiisen/repo-context-ledger/repo-context-ledger)<a href="https://agentmods.dev/skills/gviiisen/repo-context-ledger/repo-context-ledger"><img src="https://agentmods.dev/badge/skills/gviiisen/repo-context-ledger/repo-context-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/gviiisen/repo-context-ledger/repo-context-ledger"><img src="https://agentmods.dev/badge/skills/gviiisen/repo-context-ledger/repo-context-ledger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Excessive Agency · line 3 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 45 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00098 | $0.02227 |
| Opus 5 | $0.00049 | $0.01113 |
| Sonnet 5 | $0.00020 | $0.00445 |
| Haiku 4.5 | $0.00010 | $0.00223 |
Grade A, and why
repo-context-ledger 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 3d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Context Ledger
Turn behavior-changing feature work into durable, code-verified repository knowledge. Git-tracked Packs, specs, and completed Changes form the feature change ledger; cross-window and cross-Agent continuation are capabilities built on that shared source. Private vendor Memory is never read or synchronized.
First decide what is new — without a Ledger call
Judge new facts/effects from the current request, loaded conversation, known task and inspected code, not similar wording. Do this mentally: no classifier command, extra document, or automatic Git/Markdown rescan.
- Routine question/recheck/operation with sufficient context: answer or execute the authorized request normally, without a new Ledger lifecycle. Do not skip a requested recheck or infer permission to repeat side effects.
- Same known unfinished task: keep its session/epoch and background; add only new changes, findings, decisions and checks. Same-window "continue" does not require resume or a new session.
- Similar work with new behavior/inputs/paths: reuse the method, not a previous pass. Keep a suitable unfinished task; after publication create a new change record and reference relevant history. Independent deliverables stay separate.
- Missing identity/background: query only what is missing. Paused tasks and actual handovers need resume; lifecycle writes still validate ownership/epoch. Resolve stale state rather than guessing.
Proceed when scope/identity are clear, without announcing a classification checklist. Reuse results only while relevant code, inputs, environment and acceptance phase remain valid. Changed conditions and time-sensitive safety checks need fresh verification; never relabel an old pass as new. Investigate uncertain code boundaries.
Runtime
Resolve this Skill directory. Its runtime is scripts/ledger.py. After initialization use the repository entry:
python .context-ledger/ledger.py <command>
Use python3 when needed. --repo is optional; discovery walks upward to the nearest .context-ledger/config.json and stops at nested Git boundaries.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 279 B
- assets/context-pack-template.md 1.4 KB
- assets/handoff-template.md 1.7 KB
- assets/project-context-template.md 594 B
- assets/spec-template.md 1.3 KB
- assets/verify-change.py 2.2 KB runs code
- references/document-model.md 13 KB
- references/global-runtime.md 2.5 KB
- references/production-workflow.md 14 KB
- references/verification-presets.md 6.0 KB
- references/writing-quality.md 5.9 KB
- scripts/ledger.py 347 KB runs code
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.
- 3d ago Changed · +18 lines · -5 tokens per session 5ded6a55fcd3
- 12d ago First seen · 81 lines · 103 tokens per session scan A c49a692005ff
repo-context-ledger is a skill published in the GitHub repository gviiisen/repo-context-ledger (105 stars, last pushed 4d ago), licensed MIT. It adds 98 tokens to every session and 2,227 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 2026-08-30.
Other skills, from other repositories
ijfw-memory-audit
Audit and clean project memory files. Trigger: 'memory audit', 'clean memory', 'memory health', /memory-audit.
ijfw-summarize
Generate optimized project context from codebase scan. Trigger: new project, no CLAUDE.md, /ijfw-summarize.
ijfw-handoff
Session handoff generation and loading. Trigger: session end, context full, /handoff.
ijfw-recall
Surface relevant project memory at session start or on demand. Trigger: session start, 'recall', 'remember', 'what do you know', 'context', /recall.
ijfw-status
Use when the user says: 'ijfw status', 'show me the system state', 'what is ijfw doing', or to see the at-a-glance routing / memory / activity banner.
ijfw-compress
Compress memory/context files into terse form. Trigger: /compress, compress file.