agentmods.dev

speq-skill CLAUDE.md

speq-skill CLAUDE.md is an instructions file for coding agents from marconae/speq-skill. It costs 592 tokens per session, scanned A, original, MIT.

Development rules for Speq Skill, a project whose local skills are also compiled into its Claude and Codex plugin. They define which local commands, fixtures, version source, and Git practices to use.

In plain words
What is it for?
Use it when building or testing Speq Skill, changing its skills, preparing the plugin, checking versions, or creating commits.
Why use it?
Using global commands or editing generated plugin files directly can produce inconsistent builds. These rules keep local development, tests, versions, and commits aligned.

Instructions file

not rated 50 1mo ago A scan 592 tokens original MIT
View the source file marconae/speq-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.

agentmods
npx agentmods add instructions/marconae/speq-skill/claude-md
Clone the repo
git clone --depth 1 https://github.com/marconae/speq-skill

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 speq-skill CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/marconae/speq-skill/claude-md.svg)](https://agentmods.dev/instructions/marconae/speq-skill/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/marconae/speq-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/marconae/speq-skill/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 592 This file is loaded in full into every session.
When invoked 592 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00592 $0.00592
Opus 5 $0.00296 $0.00296
Sonnet 5 $0.00118 $0.00118
Haiku 4.5 $0.00059 $0.00059

Measured 4d ago against content hash 486b5823faf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speq-skill CLAUDE.md 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 4d 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.

CLAUDE.md · 22 lines

How it starts

The opening of the file, as written. The whole thing — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local Development Rules

You are building speq-skill while using it: the skills in .claude/skills/ are simultaneously this repo's dev tooling and the source that scripts/plugin/build.sh compiles into the Claude and Codex plugin.

Rules

  • CLI: always invoke the local build — ./target/debug/speq <cmd> (or ./target/release/speq <cmd> after a release build). Never the global speq or cargo run --.
  • Skill names are context-specific: /speq-* in this repo, /speq:* in the installed plugin. build.sh performs the speq-* → speq:* rename, drops the speq- folder prefix, and stamps version + author from Cargo.toml.
  • Version: Cargo.toml is the single source of truth. scripts/lib/version.sh (get_version) feeds build.sh and the docker tests — never hard-code the version anywhere else.
  • Tests: integration tests SHALL use fixtures under tests/fixtures/, not inline spec strings.
  • Git: git-agent is the only agent permitted to write git history or touch a remote; every other agent is read-only.
  • Commits follow Conventional Commits — <type>[scope]: <description> (+ optional body/footer). Types: feat (MINOR), fix (PATCH), perf, refactor, test, docs, spec, chore. Breaking change = ! after type/scope or a BREAKING CHANGE: footer (MAJOR).
  • Expert tasks: planner-agent marks reasoning-heavy tasks.md lines [expert]; speq-implement routes those to implementer-expert-agent, the rest to implementer-agent. Tag sparingly.
  • Model routing is hardcoded in each skill/agent frontmatter and stamped by build.sh — see docs/model-routing.md.
  • Markdown prose: never artificially word-wrap prose in Markdown files. Write one logical line per paragraph and list item (soft-wrap) so diffs stay line-per-thought and reflows don't churn. Do not join fenced code, tables, ASCII diagrams, YAML frontmatter, or structured **Field:** lines.
  • Mission scope: specs/mission.md is the mission for the speq CLI only — not for the skills. Skill purpose and intent live in the skill files and docs/.

Read the full file on GitHub · 22 lines

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. 4d ago First seen · 22 lines · 592 tokens per session scan A 486b5823faf5

Subscribe to this mod's changes

speq-skill CLAUDE.md is an instructions file published in the GitHub repository marconae/speq-skill (50 stars, last pushed 1mo ago), licensed MIT. It adds 592 tokens to every session, about $0.0030 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 2026-08-30.

ai-agentsartificial-intelligenceclaude-codecoding-agentskillsspec-driven-development
Related

Other instructions, from other repositories

spec-superflow GEMINI.md

Gemini CLI instructions for MageByte-Zero/spec-superflow, covering spec-superflow and spec-superflow v1.2.0 | 阶段: {{state}} | 工作流: {{workflow}}.

MageByte-Zero/spec-superflow · 178 tokens

spec-superflow copilot-instructions.md

Copilot instructions for MageByte-Zero/spec-superflow, covering phase guard, ✅ 允许操作, ⛔ 禁止操作 and 🔔 决策点.

MageByte-Zero/spec-superflow · 104 tokens

blueprint CLAUDE.md

Instructions for owainlewis/blueprint, a project described as: The best agent skills in the world for software development.

owainlewis/blueprint · 213 tokens

spec_driven_develop CLAUDE.md

Instructions for zhu1090093659/spec_driven_develop: Read AGENTS.md first. It is the shared project-level instruction source for Codex, OpenCode, Cursor, Claude Code, and other Markdown-aware coding agents.

zhu1090093659/spec_driven_develop · 168 tokens

cafleet CLAUDE.md

Claude Code instructions for himkt/cafleet, covering claude.md, skills, project: cafleet, tech stack and commands.

himkt/cafleet · 217 tokens

mine AGENTS.md

AGENTS.md instructions for 6ixGODD/mine, covering agent working agreement, source of truth, design rules, no historical baggage by default and document boundaries.

6ixGODD/mine · 2,222 tokens