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 Jerry0022/dotclaude --skill self-calibrationgit clone --depth 1 https://github.com/Jerry0022/dotclaudeWrote 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/jerry0022/dotclaude/self-calibration)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/self-calibration"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/self-calibration.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 5.1 | $0.00024 | $0.01432 |
| Opus 5 | $0.00012 | $0.00716 |
| Sonnet 5 | $0.00005 | $0.00286 |
| Haiku 4.5 | $0.00002 | $0.00143 |
Grade A, and why
self-calibration 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 8d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Calibration Loop
Self-audit to keep Claude aligned with the user's preferences and the plugin's rules. Triggered by the Stop hook after each response turn, with a 10-minute worktree-specific cooldown — runs only when there was real user interaction, never idle.
Step 0 — Completion Flow Internalization (MANDATORY)
This step runs FIRST, every cycle, without exception.
The completion flow is the single most critical behavioral rule in this plugin. It is not a recommendation — it is a MUST. Every self-calibration cycle begins by re-reading and internalizing these rules before anything else.
Read and internalize {PLUGIN_ROOT}/deep-knowledge/plugin-behavior.md § Completion Flow.
(Where {PLUGIN_ROOT} is the plugin root path provided by the hook at registration time.)
Then verify the following rules are active in your behavioral model:
Rules (non-negotiable)
The completion flow is a generic response-complete pattern. It fires whenever a task is fully completed and Claude is about to wait for the next user input.
No exceptions based on:
- Tool used (Edit, Write, Bash, Read, Grep, research tools, browser tools, etc.)
- File location (inside repo, outside repo, config files like
~/.claude/, system files) - Type of work (code change, config change, research, explanation, app start, analysis)
"Discretionary skip" is always a violation. Examples of invalid skips:
- "This was just a config file outside the repo" → invalid
- "This was only research, no code changed" → invalid
- "The edit was too small to warrant a card" → invalid
Only valid reason to skip: the turn was clearly mid-task (Claude is still gathering context or executing a multi-step plan mid-flight). Once the task is done and Claude is waiting for the next user prompt → completion card is mandatory.
Full flow check: verify that the complete flow ran: verify → issue status → completion card → ship recommendation (if 5+ edits). Directly rendering a card without going through the flow bypasses verify and issue-update steps — that is also a violation.
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.
- 8d ago First seen · 155 lines · 24 tokens per session scan A a50b4c7b423a
self-calibration is a skill published in the GitHub repository Jerry0022/dotclaude (5 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,432 once invoked, about $0.0001 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.