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 IgorWarzocha/howaboua-pi-stuff --skill instruction-calibrationgit clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuffWrote 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/igorwarzocha/howaboua-pi-stuff/instruction-calibration)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.00907 |
| Opus 5 | $0.00008 | $0.00453 |
| Sonnet 5 | $0.00003 | $0.00181 |
| Haiku 4.5 | $0.00002 | $0.00091 |
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.
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
- Start from a real request, observed failure, or explicit correction.
- State the behaviour that should change and what must remain unchanged.
- 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
- 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 -neis 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.
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.
- 10d ago First seen · 62 lines · 16 tokens per session scan A 71061717881b
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.
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.
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".
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…
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.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.