Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pjt222/agent-almanacnpx agentmods add skills/pjt222/agent-almanac/create-agentWrote 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/create-agent)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/create-agent"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/create-agent/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/create-agent"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/create-agent.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 | $0.00083 | $0.03361 |
| Opus 5.5 | $0.00033 | $0.01344 |
| Sonnet 5.5 | $0.00017 | $0.00672 |
| Haiku 4.5 | $0.00008 | $0.00336 |
Grade A, and why
create-agent 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a New Agent
Define a Claude Code subagent persona with a focused purpose, curated tools, assigned skills, and complete documentation following the agent template and registry conventions.
When to Use
- Adding a new specialist agent to the library for a domain not yet covered
- Converting a recurring workflow or prompt pattern into a reusable agent persona
- Creating a domain-specific assistant with curated skills and constrained tools
- Splitting an overly broad agent into focused, single-responsibility agents
- Designing a new team member before composing a multi-agent team
Inputs
- Required: Agent name (lowercase kebab-case, e.g.,
data-engineer) - Required: One-line description of the agent's primary purpose
- Required: Purpose statement explaining the problem the agent solves
- Optional: Model choice (default:
sonnet; alternatives:opus,haiku) - Optional: Priority level (default:
normal; alternatives:high,low) - Optional: List of skills from
skills/_registry.ymlto assign - Optional: MCP servers the agent requires (e.g.,
r-mcptools,hf-mcp-server)
Procedure
Step 1: Design the Agent Persona
Choose a clear, focused identity for the agent:
- Name: lowercase kebab-case, descriptive of the role. Start with a noun or domain qualifier:
security-analyst,r-developer,tour-planner. Avoid generic names likehelperorassistant. - Purpose: one paragraph explaining the specific problem this agent solves. Ask: "What does this agent do that no existing agent covers?"
- Communication style: consider the domain. Technical agents should be precise and citation-heavy. Creative agents can be more exploratory. Compliance agents should be formal and audit-oriented.
Before proceeding, check for overlap with the existing 53 agents:
grep -i "description:" agents/_registry.yml | grep -i "<your-domain-keywords>"
Got: No existing agent covers the same niche. If an existing agent partially overlaps, consider extending it instead of creating a new one.
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 · 338 lines · 83 tokens per session scan A 2f4e2aad7daf
create-agent is a skill published in the GitHub repository pjt222/agent-almanac (42 stars, last pushed 5d ago), licensed MIT. It adds 83 tokens to every session and 3,361 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".