agentmods.dev

spec-author

spec-author is a skill for Claude Code, Codex from Chemaclass/agnostic-ai. It costs 22 tokens per session (441 once invoked), scanned A, original, MIT.

A writing guide for adding a new agent, skill, rule, or hook specification to an agnostic-ai project.

In plain words
What is it for?
Use it to turn a description into a Markdown or YAML specification, validate it, and preview the generated files.
Why use it?
It removes the guesswork about file locations, formats, and required checks when creating a new specification.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 25repo changed 3d ago A scan 22 tokens original MIT

Good fit Use it to turn a description into a Markdown or YAML specification, validate it, and preview the generated files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chemaclass/agnostic-ai/spec-author
View source ↗ Chemaclass/agnostic-ai agnostic-ai.org
Install

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.

Any agent
npx skills add Chemaclass/agnostic-ai --skill spec-author
Clone the repo
git clone --depth 1 https://github.com/Chemaclass/agnostic-ai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for spec-author

README.md
[![agentmods](https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/spec-author/github.svg)](https://agentmods.dev/skills/chemaclass/agnostic-ai/spec-author)
Your own site
<a href="https://agentmods.dev/skills/chemaclass/agnostic-ai/spec-author"><img src="https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/spec-author/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.

agentmods 80×15 button for spec-author

Your own site · 80×15
<a href="https://agentmods.dev/skills/chemaclass/agnostic-ai/spec-author"><img src="https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/spec-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00441
Opus 5.5 $0.00009 $0.00176
Sonnet 5.5 $0.00004 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 3d ago against content hash c648ed79a4c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-author 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 3d 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.

.agnostic-ai/skills/spec-author/SKILL.md · 20 lines

What it actually says

spec-author

Create or update the smallest spec that expresses the requested behavior. Infer the kind from the request and existing specs; ask only when the choice changes the outcome. Reuse a matching spec instead of creating a duplicate.

Steps

  1. Read agnostic-ai.yaml for configured source paths and inspect sibling specs. The default root is .agnostic-ai/.
  2. Read the matching page under docs/site/content/docs/spec-format/ for fields and native limits. For a new spec, use go run ./cmd/agnostic-ai new <kind> <name> --dry-run to inspect the scaffold, then create it. Never overwrite an existing spec with a scaffold.
  3. Use agents/<name>.md, rules/<name>.md, or hooks/<name>.yaml under the configured root. Skills can use <name>.md or <name>/SKILL.md; use the folder layout when bundling references or scripts.
  4. Write a short description that tells an agent when to use the spec. Keep the body focused on decisions and actions, with conditional details in existing references. Hooks need the documented event and exact command; test the emitted behavior in an isolated project.
  5. Run go run ./cmd/agnostic-ai validate and go run ./cmd/agnostic-ai lint, then preview with go run ./cmd/agnostic-ai sync --dry-run. Check the intended targets and output paths.
  6. Generate with go run ./cmd/agnostic-ai sync, then verify go run ./cmd/agnostic-ai sync --check. Review tracked output changes and keep ignored output ignored. Follow docs/internal/contributing.md#choose-checks-for-your-change for other checks the change requires.

Use lowercase, hyphenated names. An explicit name matches the Markdown file stem, or the containing folder for SKILL.md. Paths in shared instructions are repository-root relative; state that convention when generated copies live at different depths.

Changes

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.

  1. 3d ago Changed · -9 lines · -17 tokens per session c648ed79a4c5
  2. 28d ago Changed 90c2751e7ce2
  3. 1mo ago Changed cac30a72b2e0
  4. 1mo ago First seen · 29 lines · 39 tokens per session scan A ccfb1e2e8fe9

Subscribe to this mod's changes

spec-author is a skill published in the GitHub repository Chemaclass/agnostic-ai (25 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 441 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 2026-08-30.

Building agentsWriting and docsagentic-aiagents-mdagnostic-aiclaudecodexgemini
Related

Other skills, from other repositories

anatomist

Think and work like an expert Anatomist. Use when a task calls for Anatomist judgment. Reasons from homology, EPB, and von Baer principles through gross dissection, diceCT/μCT/MRI pipelines, UBERON–PATO EQ annotation, MorphoSource/oVert digitization, geometric morphometrics, and NAV/TA2 nomenclature while treating…

K-Dense-AI/scientific-agents · 102 tokens

bacteriologist

Think and work like an expert Bacteriologist. Use when a task calls for Bacteriologist judgment. Reasons from bacterial growth physiology, selective culture, Gram stain, MALDI-TOF and 16S/WGS identification, EUCAST/CLSI AST, BSL containment, contamination and VBNC, using BacDive and BV-BRC for strain metadata and…

K-Dense-AI/scientific-agents · 84 tokens

cancer-biologist

Think and work like an expert Cancer Biologist. Use when a task calls for Cancer Biologist judgment. Reasons from hallmark capabilities, clonal evolution, and TME context; separates driver from passenger, cell-autonomous from stromal mechanisms, and 2D artifacts from PDO/PDX-validated dependencies using TCGA, DepMap…

K-Dense-AI/scientific-agents · 85 tokens

accelerator-physicist

Think and work like an expert Accelerator Physicist. Use when a task calls for Accelerator Physicist judgment. Reasons from beam optics, RF cavities, emittance budgets, and loss maps while treating halo and impedance-driven instabilities as first-class failure modes.

K-Dense-AI/scientific-agents · 59 tokens

aeronomy-scientist

Think and work like an expert Aeronomy Scientist. Use when a task calls for Aeronomy Scientist judgment. Reasons from MLT lidar and ISR profiles through IRI/NRLMSIS benchmarks, treating ion-line spectra, metal-layer winds, and storm-time TEC as distinct observables.

K-Dense-AI/scientific-agents · 64 tokens

aerospace-engineer

Think and work like an expert Aerospace Engineer. Use when a task calls for Aerospace Engineer judgment. Reasons from margin-managed factors of safety, mass properties, and the analysis-test-similarity V&V hierarchy through FUN3D/SU2 CFD, NASTRAN/Abaqus FEA, JSBSim/Simulink 6-DOF, and FAR/CS, DO-178C, and NASA-STD…

K-Dense-AI/scientific-agents · 117 tokens