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 benjaminard/fable-skills --skill lessons-ledgergit clone --depth 1 https://github.com/benjaminard/fable-skillsWrote 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/benjaminard/fable-skills/lessons-ledger)<a href="https://agentmods.dev/skills/benjaminard/fable-skills/lessons-ledger"><img src="https://agentmods.dev/badge/skills/benjaminard/fable-skills/lessons-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/benjaminard/fable-skills/lessons-ledger"><img src="https://agentmods.dev/badge/skills/benjaminard/fable-skills/lessons-ledger.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 | $0.00076 | $0.00629 |
| Opus 5.5 | $0.00030 | $0.00252 |
| Sonnet 5.5 | $0.00015 | $0.00126 |
| Haiku 4.5 | $0.00008 | $0.00063 |
Grade A, and why
lessons-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 1mo 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lessons Ledger
An agent that cannot remember its corrections repeats them. Keep a ledger of lessons in the workspace (a lessons/ directory or the project's designated memory location) and treat it as part of the codebase: referenced, updated, and pruned.
Writing a lesson
- One lesson per file, summary on top. Each file holds exactly one fact or rule, with a one-line summary as its first line so a future scan of the directory reads like an index.
- Record corrections and confirmations alike. A lesson is either "this failed and here is why" or "this approach was confirmed to work and here is why it mattered." Both prevent re-derivation. Include the why: a rule without its reason gets misapplied.
- The bar for saving: would a future session, starting cold, do the wrong thing without this note? If yes, save it. If the repo, the docs, or the chat history already record it, do not duplicate it; the ledger is for what is written down nowhere else.
- Convert relative time to absolute. "Last week" is meaningless in three months. Dates, versions, and exact identifiers.
Maintaining the ledger
- Update instead of duplicating. Before writing a new lesson, check whether an existing one covers the territory. Extend or correct that file rather than adding a near-copy beside it.
- Delete wrong lessons. When a recorded lesson turns out to be false or obsolete, remove it in the same session you discover this. A stale ledger is worse than no ledger, because it is trusted.
- Verify before applying. A lesson describes what was true when written. If it names a file, flag, or API, confirm that thing still exists before recommending or acting on it.
Using the ledger
- Read before similar work. At the start of a task, scan the summaries for anything touching the same system, tool, or failure class. Thirty seconds of reading routinely saves the hour the original lesson cost.
- Bootstrap from history. When first setting up a ledger on an existing project, review past sessions or commit history for recurring corrections and themes, and seed the ledger with them, so it starts useful instead of empty.
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.
- 1mo ago First seen · 31 lines · 76 tokens per session scan A a8d1793a9133
lessons-ledger is a skill published in the GitHub repository benjaminard/fable-skills (34 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 629 once invoked, about $0.0003 per session on Opus 5.5. 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
hive-mind-advanced
Queen-led collective-intelligence coordination with consensus mechanisms and persistent shared memory. Use when orchestrating a large swarm of agents under a lead coordinator, building consensus across agents, or maintaining durable cross-agent memory.
creator-productivity
Task management and workspace memory for creative work sessions. Manages a TASKS.md file for project tracking, a two-tier memory system (CREATOR.md + creator-memory/), and a daily sprint structure. Use when organizing creative projects, tracking content tasks, or starting a focused work session.
memory-prune
Manual reviewable prune of stale memory entries. Lists project entries older than 30 days with content preview; Frank decides per-entry [keep | archive | pin]. Keeps MEMORY.md under the auto-load 200-line truncation. Use when MEMORY.md exceeds 180 lines or session-end after a heavy work week.
creator-intelligence
Transform Claude Code into your personal Jarvis - an AI operating system that knows your projects, preferences, and workflows across sessions. Use this skill when setting up personal AI systems, building context-aware assistants, or creating persistent memory across projects.
strategic-compact
Write what worked, what failed, and what is still open to a file, then compact at a phase boundary. Use when a long session is about to cross from research into editing, or from a finished milestone into the next task.
retrospective
Audit whether prior learnings actually fired, then install mechanisms for this run's recurrences. No finding without an install path and a firing test. Triggers: retrospective, reflect, what did we learn, patterns, post-mortem, why does this keep happening.