instruction-calibration

instruction-calibration is a skill for Claude Code, Codex from IgorWarzocha/howaboua-pi-stuff. It costs 16 tokens per session (907 once invoked), scanned A, original, MIT.

A testing guide for tuning reusable skills or agent instructions based on observed behavior.

In plain words
What is it for?
Use it to create probe cases, run visible comparisons between coding agents, and inspect available controls for context files, instructions, skills, plugins, and extensions.
Why use it?
It helps isolate the behavior that should change, preserve what already works, and compare results on representative requests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to create probe cases, run visible comparisons between coding agents, and inspect available controls for context files, instructions, skills, plugins, and extensions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/igorwarzocha/howaboua-pi-stuff/instruction-calibration
Install

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.

Any agent
npx skills add IgorWarzocha/howaboua-pi-stuff --skill instruction-calibration
Clone the repo
git clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuff

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for instruction-calibration

README.md
[![agentmods](https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/instruction-calibration/github.svg)](https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/instruction-calibration)
Your own site
<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/instruction-calibration"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/instruction-calibration/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.

agentmods 80×15 button for instruction-calibration

Your own site · 80×15
<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/instruction-calibration"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/instruction-calibration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 907 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00907
Opus 5 $0.00008 $0.00453
Sonnet 5 $0.00003 $0.00181
Haiku 4.5 $0.00002 $0.00091

Measured 10d ago against content hash 71061717881b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

instruction-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 10d 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.

packages/pi-skill-harness-and-agent-engineering/skills/instruction-calibration/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

For reusable skill structure, also load an applicable skill-authoring skill. This skill owns behavioural calibration, not package shape.

Define the delta

  1. Start from a real request, observed failure, or explicit correction.
  2. State the behaviour that should change and what must remain unchanged.
  3. Prepare a small probe set:
    • the natural request that exposed the failure
    • the nearest request that should produce a different choice
    • an unrelated request where the instruction should stay out of the way
  4. Give test agents only the task and context they cannot access. Do not hide the desired method inside the probe.

Keep the user in the comparison

  • The easiest setup is tmux or Herdr, with each tested agent in a visible sibling pane beside the current session. Preserve the current workspace, working directory, and user focus unless the comparison requires another environment. In Herdr, consult herdr --skill.
  • Do not hide calibration in a background subagent or detached process.
  • Inspect the tested coding agent's current help for controls over context files, reusable instructions, skills, plugins, and extensions. Start with the fewest local instruction layers, state anything that cannot be disabled, then restore layers progressively.
  • For Pi, pi -nc -ns -ne is the local raw starting point. Use current help to add only the candidate skill or prompt before restoring the natural environment.
  • After each meaningful run, identify the pane, prompt, and loaded instruction layers, give only an initial observation or suggested next probe, then stop for the user to read both sessions.
  • Do not revise the candidate, decide the disposition, or close test runs before the user responds. Leave every pane open until the user permits cleanup.
  • Allow natural follow-up prompts in the same test session, including asking the model to diagnose or improve its answer. Treat them as exploration, not fresh baseline evidence.
  • After changing a loaded skill, prompt, context file, or environment layer, use the harness reload path only for a WIP check. Relaunch a fresh session for comparison evidence. Keep superseded runs visible but exclude them from clean comparisons.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 10d ago First seen · 62 lines · 16 tokens per session scan A 71061717881b

Subscribe to this mod's changes

instruction-calibration is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (359 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 907 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 2026-08-30.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens