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 agentmods add skills/aaronb305/claude-cortex/ledger-knowledgenpx skills add aaronb305/claude-cortex --skill ledger-knowledgegit clone --depth 1 https://github.com/aaronb305/claude-cortexWrote 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/aaronb305/claude-cortex/ledger-knowledge)<a href="https://agentmods.dev/skills/aaronb305/claude-cortex/ledger-knowledge"><img src="https://agentmods.dev/badge/skills/aaronb305/claude-cortex/ledger-knowledge.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 | $0.00061 | $0.00880 |
| Opus 5 | $0.00030 | $0.00440 |
| Sonnet 5 | $0.00012 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
ledger-knowledge 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ledger Knowledge Skill
This skill provides access to the claude-cortex knowledge ledger, enabling retrieval of learnings from previous sessions.
Ledger Locations
- Global ledger:
~/.claude/ledger/- Knowledge across all projects - Project ledger:
./.claude/ledger/- Project-specific knowledge
Ledger Structure
ledger/
├── blocks/ # Immutable learning blocks (JSON)
│ ├── abc123.json
│ └── def456.json
├── index.json # Chain index with block references
└── reinforcements.json # Confidence scores and outcome counts
Commands
List learnings
uv run cclaude list [options]
Options:
--min-confidence 0.7- Filter by confidence threshold--category discovery- Filter by category--limit 20- Limit results-p .- Query project ledger instead of global
Show learning details
uv run cclaude show <learning_id>
Verify chain integrity
uv run cclaude verify
Learning Categories
| Category | Description |
|---|---|
| discovery | New information about codebases, APIs, patterns |
| decision | Architectural choices and rationale |
| error | Mistakes to avoid, gotchas, failed approaches |
| pattern | Reusable solutions, conventions, templates |
Confidence Levels
- 0.9-1.0: Highly reliable, proven through multiple successes
- 0.7-0.9: Reliable, has positive outcome history
- 0.5-0.7: Moderate, initial learnings or mixed outcomes
- 0.3-0.5: Uncertain, may need verification
- 0.0-0.3: Unreliable, consider reviewing or removing
Usage Examples
Find patterns for authentication:
uv run cclaude list --category pattern | grep -i auth
Get high-confidence learnings:
uv run cclaude list --min-confidence 0.8
Check project-specific knowledge:
uv run cclaude list -p . --limit 10
Full-Text Search
MCP Tools (Preferred)
Use MCP tools for fastest access:
search_learnings("query")- Full-text search with BM25 rankingsearch_learnings("query", category="pattern")- Filtered searchget_learning("abc123")- Get full learning detailslist_learnings(min_confidence=0.7)- List by confidenceledger_stats()- Ledger statistics
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 First seen · 128 lines · 61 tokens per session scan A a54b7a4650d6
ledger-knowledge is a skill published in the GitHub repository aaronb305/claude-cortex (2 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 880 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…