A documentation system for organizing AGENTS.md files and engineering specifications. It separates implementation rules, product requirements, and technical decisions into clearly defined documentation folders.

Auditing, reorganizing, splitting, migrating, and maintaining agent instructions and engineering specifications.

It reduces conflicting or scattered instructions by giving agents a shared map and a single home for each kind of information.

agents-spec — Skill for Codex by leftzzzz/agents-spec-skill

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 leftzzzz/agents-spec-skill --skill agents-spec

Clone the repo

git clone --depth 1 https://github.com/leftzzzz/agents-spec-skill

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/leftzzzz/agents-spec-skill/agents-spec/github.svg)](https://agentmods.dev/skills/leftzzzz/agents-spec-skill/agents-spec)

Your own site

<a href="https://agentmods.dev/skills/leftzzzz/agents-spec-skill/agents-spec"><img src="https://agentmods.dev/badge/skills/leftzzzz/agents-spec-skill/agents-spec/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/leftzzzz/agents-spec-skill/agents-spec"><img src="https://agentmods.dev/badge/skills/leftzzzz/agents-spec-skill/agents-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,486 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

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 Memory Poisoning · line 53
Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.

Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00121	$0.03486
Opus 5.5	$0.00048	$0.01394
Sonnet 5.5	$0.00024	$0.00697
Haiku 4.5	$0.00012	$0.00349

Measured 1mo ago against content hash 6d0df8c3d4a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agents-spec 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit_agents_md.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/agents-spec/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS Spec

Core Model

Use a cross-agent documentation model:

Keep root AGENTS.md as the shared boot map and documentation router.
Keep only current, implementation-facing engineering facts and rules in docs/specs/ as the single live Spec source.
Keep each fact or rule in one authoritative body. A Spec must not contain history, change summaries, progress snapshots, release records, background narrative, or unrelated description.
Keep product intent, acceptance criteria, and product decisions in docs/requirements/.
Keep architecture, implementation plans, and technical decisions in docs/technical/.
Keep real AGENTS.md navigation entrypoints in all three documentation directories.
Do not depend on nested AGENTS.md auto-discovery. Make root explicitly tell every agent when to read or search each directory.
Do not use .agents/projects/ or .agents/references/ as the canonical Spec store.

Use this default layout:

AGENTS.md
CLAUDE.md -> AGENTS.md       # Optional; create only on explicit user request
docs/
  specs/
    AGENTS.md
    projects/
    references/
  requirements/
    AGENTS.md
  technical/
    AGENTS.md

Preserve an existing useful subdivision under docs/specs/; projects/ and references/ are defaults, not mandatory empty directories.

Document Responsibilities

Classify a statement by what it governs:

Agent instruction: state how an agent must act or where it must look.
Engineering Spec: state what the code or system must satisfy now, such as a standard, contract, protocol, security policy, compatibility boundary, or operational invariant.
Requirement document: record the product or business outcome, why it matters, acceptance criteria, and product decisions.
Technical document: record architecture, implementation approach, tradeoffs, and technical decisions.

Do not use docs/specs/ as a generic home for every document called a "spec." Split a mixed document by responsibility: move business intent and acceptance criteria to docs/requirements/, current verifiable engineering facts and rules to docs/specs/, and design rationale, migration plans, audits, postmortems, status reports, and historical records to docs/technical/.

Read the full file on GitHub · 214 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed · +16 lines · +16 tokens per session 6d0df8c3d4a5
1mo ago Changed · +12 lines · +7 tokens per session 5d31618f7726
2mo ago First seen · 186 lines · 98 tokens per session scan A 4052484d7cee

Subscribe to this mod's changes

agents-spec is a skill published in the GitHub repository leftzzzz/agents-spec-skill (37 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 3,486 once invoked, about $0.0005 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 agents Writing and docs

agents-spec next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agents-specleftzzzz/agents-spec-skill	Skill	37	1mo ago	MIT	A	121	Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code