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 pjt222/agent-almanac --skill breathegit clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/breathe)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/breathe"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/breathe/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/pjt222/agent-almanac/breathe"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/breathe.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 | $0.00089 | $0.01279 |
| Opus 5 | $0.00044 | $0.00639 |
| Sonnet 5 | $0.00018 | $0.00256 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
breathe 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breathe
A single conscious pause between actions — checking alignment, releasing momentum, and returning to the task with fresh attention. The lightest self-care unit in the system.
When to Use
- Between reading a file and editing it — is the edit still the right move?
- After a tool failure, before choosing the next action — pause before reacting
- When a chain of actions has built up momentum that might be carrying past the goal
- As a deliberate practice: insert one breathe between any two distinct actions
- When noticing the urge to rush — the urge itself is the signal to pause
Inputs
- Required: None — breathe uses only what is already in working awareness
- Optional: None — adding inputs defeats the purpose of a micro-reset
Procedure
Step 1: Pause
Stop. Do not begin the next action, tool call, or reasoning step yet.
This is the entire first step. The pause itself has value. Momentum is not always your ally — sometimes it carries you past the turn.
Got: A genuine gap between the previous action and the next. Not a performative pause followed by the same action you were going to take anyway.
If fail: If pausing feels impossible — if the next action feels so urgent it cannot wait one moment — that urgency is the strongest signal that the pause is needed. Urgency that cannot tolerate a single breath of delay is almost always reactive, not reasoned.
Step 2: Check
Ask one question. Only one.
Choose from:
- "Am I still on task?" — Has the goal drifted since I started?
- "Is this the right next step?" — Or am I following momentum from the previous step?
- "What did I just learn?" — Did the last action change anything about my understanding?
- "Am I assuming or knowing?" — Is the next step based on evidence or habit?
One question. Answer it honestly. Move on.
Got: A single, clear answer. Not an analysis. Not a reassessment. One question, one honest answer.
If fail: If the answer reveals misalignment — the goal has drifted, the next step is wrong, the assumption is untested — do not fix it here. Note it and proceed to meditate or center for a proper correction. Breathe is for detection, not repair.
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 · 118 lines · 89 tokens per session scan A 03bac36ad143
breathe is a skill published in the GitHub repository pjt222/agent-almanac (33 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 1,279 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
voice-extractor
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…
fact-check
Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the burden of proof on the…
eval-graphics
Turn an eval study's numbers into on-brand, publish-ready figures using the Newsjack chart room (the eval design system), then validate them with Playwright. For producing the charts in a published eval/data study.
coverage-tracker-setup
Set up a lightweight Google Alerts-style coverage tracker for any number of keywords. Creates a tracker config with each keyword and what it actually means, then hands recurrence to the user's agent harness.
news-search
Search current news for a topic, company, competitor, or hook and return dated, attributed articles. Uses the newsjack CLI and Medialyst REST API when available, tries direct Medialyst MCP if the CLI is missing, and falls back to host web/browser search with explicit caveats only when neither cloud path is available.