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.
git 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/commands/igorwarzocha/howaboua-pi-stuff/tune-comms)<a href="https://agentmods.dev/commands/igorwarzocha/howaboua-pi-stuff/tune-comms"><img src="https://agentmods.dev/badge/commands/igorwarzocha/howaboua-pi-stuff/tune-comms/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/commands/igorwarzocha/howaboua-pi-stuff/tune-comms"><img src="https://agentmods.dev/badge/commands/igorwarzocha/howaboua-pi-stuff/tune-comms.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 | $0.00026 | $0.00453 |
| Opus 5.5 | $0.00010 | $0.00181 |
| Sonnet 5.5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
tune-comms 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 2d 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.
What it actually says
Read this plugin's communication source before you write anything. Start with skills/communication/SKILL.md and skills/communication/references/conversation.md, both relative to the h-stack plugin directory. Those files are the source the command reads. They are not an always-on skill. Do not look for them in the repository you are tuning, and do not create them there.
Infer what that repository is about from its documents, names, and the work in front of you. Write the tune in that voice. A games catalogue tunes toward a gaming voice using these principles, not a generic assistant voice.
Use another file in this plugin's skills/communication/references/ only when that reference belongs to the subject. Do not invent a reference the source does not have. There is no gaming file to add.
Apply the communication principles while you write. Cut ceremonial openings, inflated stakes, and a voice that could belong to any product. Keep the punctuation, sentence, and actor rules from the source. Do not add a personal name.
Save the tune on one surface, the one this session already treats as durable instructions. Revise an existing tune instead of adding a second copy. Do not open a branch or pull request only to save it.
- When this is a Cursor cloud project, write it into the project store's reusable guidance,
preferences.md. Create that file if it is missing. Later agents on this project read that store. Stop there. Do not also editAGENTS.mdor a project rule, and do not open a branch or pull request. - Otherwise, when both
AGENTS.mdand.cursor/rules/exist, update the one this session already loaded as the agent contract. Do not write the tune into both. - Otherwise, when this repository's agent contract is
AGENTS.md, update that file in the working tree. - Otherwise, when this repository's agent contract is a Cursor project rule, add one always-applied
.mdcrule under.cursor/rules/. Put the tune in the rule body.
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.
- 2d ago First seen · 20 lines · 26 tokens per session scan A 1c8b563fe372
tune-comms is a command published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (402 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 453 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 2026-10-16.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.