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/rohitgehe05/mindpowers/calibratingnpx skills add rohitgehe05/mindpowers --skill calibratinggit clone --depth 1 https://github.com/rohitgehe05/mindpowersWrote 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/rohitgehe05/mindpowers/calibrating)<a href="https://agentmods.dev/skills/rohitgehe05/mindpowers/calibrating"><img src="https://agentmods.dev/badge/skills/rohitgehe05/mindpowers/calibrating.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 | $0.00058 | $0.01000 |
| Opus 5 | $0.00029 | $0.00500 |
| Sonnet 5 | $0.00012 | $0.00200 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
calibrating 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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Calibrating
Overview
mindpowers does one loop: shape, draft, review, fact-check, and remember what you like. This skill is the "remember" step, and the only one that writes docs/mindpowers/preferences.md. mindstorming step 1 reads that file before it starts a new session, so what gets recorded here shapes every future spec of that template type.
This is a light skill. Don't turn it into an interrogation: most of the time there are 1-3 short questions and one write.
User-Facing Language
Think precisely; respond plainly. Use common words and short sentences. Explain an unavoidable technical term the first time it appears, and give one short example when a rule could be misunderstood. For a material conclusion about a preference or proposed write, give a compact explanation: the recommendation or conclusion, what you checked, the main reasons, uncertainty, and the next step. Do not dump internal machinery. If the user says the explanation is unclear, explain it again from scratch.
Process
- Identify what this is about. Figure out which spec/draft the feedback concerns. Scan
docs/mindpowers/specs/anddocs/mindpowers/drafts/for a matching topic or recent file; if it's genuinely ambiguous, ask which one. Note its templatetype: preferences are filed under that type. - Compare supplied versions first. When the user supplies or points to both the Mindpowers draft and the final human-edited artifact, compare them before asking questions. Identify meaningful changes and infer their likely intent from context. Ask only about meaningful changes whose intent cannot be inferred.
- Ask at most 3 questions, skipping any already answered by what the user said or by the comparison:
- What landed: what worked and should happen again?
- What got cut or rewritten by a human: where did the draft miss?
- What should change next time?
- Distill into 1-3 one-line preference entries. Record only stable preferences, not a general evaluation of the product, field, or artifact. Keep entries short, concrete, reusable, and distinct from a summary of the conversation.
- Show the entries and get approval before writing. Let the user edit the wording.
- Append to
docs/mindpowers/preferences.mdunder the matching template's section.
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.
- 5d ago First seen · 67 lines · 58 tokens per session scan A 9d0d6c89302c
calibrating is a skill published in the GitHub repository rohitgehe05/mindpowers (5 stars, last pushed 27d ago), licensed MIT. It adds 58 tokens to every session and 1,000 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
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
assigns-audit
Inspect LiveView socket assigns for memory bloat — missing temporaryassigns, unused assigns, unbounded lists needing streams, memory estimates. Use when LiveView memory grows or you need to add temporaryassigns.
compound
Capture solved problems as searchable solution docs. Use after fixing bugs, when "that worked", or after successful /phx:review or /phx:investigate.
recall
Recall prior work from past sessions — how a bug was fixed, what was decided, where a pattern lives. Use when asked 'have we done this before' or 'how did I fix X' in Elixir/Phoenix work. ccrider MCP when available, else git + solution docs.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
context-anchoring
Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development. Scoped to feature-level work — design, implementation, bugfix, refactor — not for codebase-wide assessments or product-wide specifications (those define their own document lifecycles).…