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 OutlineDriven/odin-claude-plugin --skill history-notesgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/history-notes)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/history-notes"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/history-notes/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/outlinedriven/odin-claude-plugin/history-notes"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/history-notes.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 | $0.00031 | $0.01039 |
| Opus 5.5 | $0.00012 | $0.00416 |
| Sonnet 5.5 | $0.00006 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
history-notes 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
History note capture
Contract
| Field | Bound contract |
|---|---|
| Trigger | User says remember this or settles one durable fact. |
| Authority | Reversible local: writes only to the named append-only note store; rollback is undo. No remote mutation. |
| Side effect | Appends one schema-validated, redacted note to the local JSONL store; no other file, VCS, credential, or remote mutation. |
| Done | One bounded self-contained fact is strict UTF-8 JSONL with RFC3339 time, project, and optional tags; it is redacted, indexed, and recallable; transcript and code-obvious content is rejected. |
Inputs
- Required: the durable fact text the user supplied, and the project identifier.
- Optional: tags.
- The local append-only note store path.
Procedure
- Identify the durable fact from the user's remember-this statement or settled fact. Bound scope to one self-contained fact; if several were supplied, capture the first and stop, or ask once for the single item to capture. Done when: one self-contained fact is identified from the user statement, and if several were supplied, the first is captured and the rest are stopped or deferred with one clarification ask.
- Reject the fact if it is verbatim transcript content, conversation echo, or obvious from the current code (restates a function signature, file path, or visible state). Stop with rejected-content; do not append. Done when: the fact is confirmed not verbatim transcript, conversation echo, or code-obvious (function signature, file path, visible state), and if it is, the run stops with rejected-content and no append.
- Redact secrets and PII from the fact text: replace credentials, API keys, paths under the user home, email addresses, and numeric identifiers with a redaction marker. If redaction would erase the fact's meaning, stop with rejected-content. Done when: secrets and PII are replaced with redaction markers in the fact text, and if redaction would erase the fact meaning, the run stops with rejected-content and no append.
- Validate the redacted fact is non-empty, strict UTF-8, and bounded to one sentence or one short clause; reject paragraphs. Done when: the redacted fact is confirmed non-empty, strict UTF-8, and bounded to one sentence or one short clause, and paragraphs are rejected.
- Build one JSONL object with fields time (RFC3339 UTC), project, fact (redacted), and tags (optional, omitted when none). Done when: one JSONL object is built with fields time (RFC3339 UTC), project, fact (redacted), and tags (optional, omitted when none), and every required field is present.
- Append the line to the local append-only note store at the configured path; create the file if absent. Do not overwrite or edit prior lines. Done when: the JSONL line is appended to the store at the configured path, the file is created if absent, and no prior line is overwritten or edited.
- Index the new line by project and tags so it is recallable by later search. Done when: the new line is indexed by project and tags, and a search by project returns the appended line.
- Confirm recallability: read the store back and locate the appended line by its time and project. Done when: the store is read back and the appended line is located by its time and project, confirming recallability.
What ships with it
1 file 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.
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 · 45 lines · 31 tokens per session scan A 9973add3417a
history-notes is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (39 stars, last pushed 25d ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,039 once invoked, about $0.0001 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 2026-09-13.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…