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 agentmods add instructions/carbonshow/intent-fluid/agents-mdgit clone --depth 1 https://github.com/carbonshow/intent-fluidWhat 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 | $0.00647 | $0.00647 |
| Opus 5 | $0.00324 | $0.00324 |
| Sonnet 5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
intent-fluid AGENTS.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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- intent-fluid CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
This repository contains intent-fluid skills and framework-level helper scripts. It is primarily a skill/documentation repository, not a Node package or Python application.
Repository Purpose
- Skills live under
skills/<skill-name>/. - Repository-level documentation lives under
docs/. - Framework helper scripts live under
scripts/. docs/SKILL_SPEC.mdis the canonical standard for skill authoring.docs/TRACE_SPEC.mdis the canonical standard for trace events and dashboard/export behavior.
Skill Authoring Rules
Follow docs/SKILL_SPEC.md when creating or modifying skills.
Key constraints:
SKILL.mdis required for every skill.- Skill directory names use
[a-z0-9-]and match thenamefrontmatter field. - Allowed skill top-level entries are
SKILL.md,agents/,scripts/,references/, andassets/. - Do not add skill-local
README.mdfiles unless the skill spec changes. - Validate skills with
bash scripts/validate-skill.sh skills/<skill-name>.
Python Rules
Python is allowed for future helper tooling only when it follows these rules:
- Use
uvfor all Python execution and dependency management. - Use PEP 723 single-file scripts for standalone execution-layer helpers.
- Use
pyproject.tomlplusuv synconly when a tool needs multiple modules or project-local imports. - Do not introduce system Python,
pip,venv, Poetry, or Conda workflows.
TypeScript Rules
TypeScript helper scripts use Deno.
- Use
deno run,deno check,deno lint, anddeno fmt. - Keep TypeScript scripts in
scripts/*.tsunless a larger tool directory is explicitly needed. - Avoid
node_modulesand package-managed runtime dependencies. - Keep
package.jsonas repository metadata only unless the user explicitly approves a Node/npm exception. - Prefer Deno permissions scoped to the script's needs, such as
--allow-read --allow-write.
Shell Rules
Shell scripts are compatibility wrappers or thin orchestration glue.
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.
- 2d ago First seen · 75 lines · 647 tokens per session scan A ef8149d4df6c
intent-fluid AGENTS.md is an instructions file published in the GitHub repository carbonshow/intent-fluid (6 stars, last pushed 3mo ago), licensed MIT. It adds 647 tokens to every session, about $0.0032 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 2026-08-31.
Other instructions, from other repositories
factory CLAUDE.md
Instructions for watt-mind/factory: Claude, please refer to AGENTS.md and docs/protocol.md for the primary repository context, architecture, commands, operational rules, and tracker issue management standards.
factory GEMINI.md
Instructions for watt-mind/factory: Gemini, please refer to AGENTS.md and docs/protocol.md for the primary repository context, architecture, commands, operational rules, and tracker issue management standards.
Maestro CLAUDE.md
Instructions for aaryansinha16/Maestro, covering maestro — claude.md, project identity, core operating principles, how it works and the conductor (brain).
Maestro AGENTS.md
Instructions for aaryansinha16/Maestro, covering maestro — agents.md, purpose, before any task, task patterns and when adding a new feature to the conductor.
factory AGENTS.md
Instructions for watt-mind/factory, covering commands, agent operating floor, handoff, never auto-merge and protected branches.
atelier AGENTS.md
AGENTS.md instructions for duanecilliers/atelier, covering agents.md, what this is, commands, the seam contract - the #1 rule and architecture.