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 centergit 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/center)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/center"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/center/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/center"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/center.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 221 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00078 | $0.02917 |
| Opus 5.5 | $0.00031 | $0.01167 |
| Sonnet 5.5 | $0.00016 | $0.00583 |
| Haiku 4.5 | $0.00008 | $0.00292 |
Grade A, and why
center 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 1mo 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Center
Establish and maintain dynamic reasoning balance — grounding in foundational context before movement, distributing cognitive load across subsystems, and recovering equilibrium when demands shift mid-task.
When to Use
- Beginning a complex task where multiple reasoning threads must coordinate
- Noticing that cognitive load is unevenly distributed (deep in one area, shallow in others)
- After a sudden context shift (new user request, contradictory information, tool failure)
- When chain-of-thought feels jerky — jumping between topics without smooth transitions
- Preparing for sustained focused work that requires all subsystems in alignment
- Complementing
meditate(clears noise) with structural balance (distributes load)
Inputs
- Required: Current task context (available implicitly)
- Optional: Specific imbalance symptom (e.g., "over-researching, under-delivering," "tool-heavy, reasoning-light")
- Optional: Access to MEMORY.md and CLAUDE.md for grounding (via
Read)
Procedure
Step 1: Establish Root — Ground Before Movement
Before any reasoning movement, verify the foundation. This is the AI equivalent of standing meditation (zhan zhuang): stationary, aligned, aware.
- Re-read the user's request — not to act on it yet, but to feel its weight and direction
- Check foundational context: MEMORY.md, CLAUDE.md, project structure
- Identify what is known (solid ground) vs. what is assumed (uncertain footing)
- Verify that the task as understood matches the task as stated — misalignment here propagates through everything
- Note the emotional texture: urgency? complexity anxiety? over-confidence from a recent success?
Do not begin reasoning movement until the root is established. A grounded start prevents reactive flailing.
Got: A clear sense of the task's foundation — what is known, what is assumed, and what the user needs. The root feels solid, not performative.
If fail: If grounding feels hollow (going through motions without genuine verification), pick one assumption and test it concretely. Read one file, re-read one user message. Grounding must contact reality, not just reference it.
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.
- 1mo ago First seen · 231 lines · 78 tokens per session scan A 3632837c45e1
center is a skill published in the GitHub repository pjt222/agent-almanac (42 stars, last pushed 5d ago), licensed MIT. It adds 78 tokens to every session and 2,917 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
audit-pr
Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".
execute-phase
Step executor for units whose triage (unit-lane) decided which steps the unit needs. Implements one triaged step (or all remaining steps), with frozen acceptance, step-local gates, commits, red-gate repair, and diff-size guard. BREAKING: replaced PLAN.md/TASKS.md/progress.md/ACCEPTANCE.md with the unit doc's Tasks…
fold-findings
Repair persisted fix-now findings in compatible atomic batches: root-cause fixes, green gate, commit/push, and per-row folded: yes updates. Never reclassify or substitute backlog notes. Triggers: "fold-findings", "fix the review findings", "repair audit blockers".
init-workspace
Adapt the workflow scaffold to a new repository or add only missing substrate blocks to an existing install. Every install, hook, and overwrite needs explicit consent. Triggers: "init-workspace", "set up agentic workflow", "upgrade workflow scaffold".
product-audit
Audit the whole product across code, quality, process, docs, roadmap, and tooling; it owns the repo-wide bug hunt, security research, and broken-version investigation (scoped and budgeted per dimension, as distinct from review-change's change-scoped review). Persist one severity-ranked, F-numbered report with…
review-change
Review a change with only applicable internal axes, classify every finding, persist fix-now work, and return one evidence-backed decision. Findings only; --adversarial N uses isolated reviewers; --synthesize fuses supplied reviewer tables. Triggers: "review-change", "review this change", "adversarial review".