min-specs

min-specs is a skill for Claude Code, Codex from fzfclee/consulting-skills. It costs 49 tokens per session (703 once invoked), scanned A, original, Apache-2.0.

A method for defining the smallest set of conditions that must be true for a plan, deal, product, or change to work. It turns requirements into clear proceed, adjust, or stop checks.

In plain words
What is it for?
Use it to set must-have requirements, no-go criteria, constraints, and success conditions for decisions or proposals.
Why use it?
It prevents wish lists and unnecessary work from hiding conditions that make an action unworkable.

Skill for Claude CodeCodex

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

Good fit Use it to set must-have requirements, no-go criteria, constraints, and success conditions for decisions or proposals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fzfclee/consulting-skills/min-specs
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 fzfclee/consulting-skills --skill min-specs
Clone the repo
git clone --depth 1 https://github.com/fzfclee/consulting-skills

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 min-specs

README.md
[![agentmods](https://agentmods.dev/badge/skills/fzfclee/consulting-skills/min-specs/github.svg)](https://agentmods.dev/skills/fzfclee/consulting-skills/min-specs)
Your own site
<a href="https://agentmods.dev/skills/fzfclee/consulting-skills/min-specs"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/min-specs/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 min-specs

Your own site · 80×15
<a href="https://agentmods.dev/skills/fzfclee/consulting-skills/min-specs"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/min-specs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 703 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 $0.00049 $0.00703
Opus 5 $0.00024 $0.00351
Sonnet 5 $0.00010 $0.00141
Haiku 4.5 $0.00005 $0.00070

Measured 10d ago against content hash 005ec1f22555, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

min-specs 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 10d 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.

skills/min-specs/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Min Specs

Use this skill to define the smallest set of must-have conditions that make an action viable.

Method Notes

  • Min Specs identify what is truly required, not a wish list.
  • The method helps prevent overbuilding, over-negotiating, and pursuing deals that cannot work.
  • A good Min Spec is binary enough to guide proceed / adjust / stop decisions.

Required Inputs

Collect or infer these inputs before execution:

  • desired outcome
  • proposed action, deal, solution, or change
  • constraints and non-negotiables
  • known failure modes
  • stakeholder or customer requirements

If an input is missing, mark it as missing, state the assumption used, and add a validation action.

When Not To Use

Do not use when the user needs to rank attractive options rather than define viability. Use decision-matrix, weighted-scorecard, or wsjf-prioritization instead.

Step-by-Step Execution

Step Required input How to execute Output
Define success Desired outcome, decision boundary. State what must be true for the initiative to be considered successful. Success definition.
List possible requirements Stakeholder needs, constraints, risks, operating needs. Create a broad list of candidate conditions. Requirement pool.
Remove nice-to-haves Candidate requirements, success definition. Ask whether success fails without this condition. If not, move it to nice-to-have. Trimmed requirements.
Convert to minimum specs Must-have conditions. Rewrite each condition as observable, testable, and binary where possible. Min Specs list.
Define no-go criteria Failure modes, risk tolerance, constraints. State what would make the action non-viable or require redesign. No-go list.
Link to next action Current plan, validation access, owners. Decide what to confirm first and what action is allowed before confirmation. Decision gate.

Output Template

### 1. Success Definition
- Desired outcome:
- Decision boundary:
- What would count as failure:

### 2. Min Specs
| Minimum condition | Why it is required | Evidence now | How to verify | Pass / fail / unknown |
|---|---|---|---|---|
|  |  |  |  |  |

### 3. Nice-To-Haves Removed
- Nice-to-have:
- Why it is not required now:

### 4. No-Go Criteria
| No-go condition | Trigger signal | Response |
|---|---|---|
|  |  |  |

### 5. Decision Gate
- Proceed if:
- Adjust if:
- Stop if:
- First thing to verify:

Read the full file on GitHub · 80 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. 10d ago First seen · 80 lines · 49 tokens per session scan A 005ec1f22555

Subscribe to this mod's changes

min-specs is a skill published in the GitHub repository fzfclee/consulting-skills (4 stars, last pushed 22d ago), licensed Apache-2.0. It adds 49 tokens to every session and 703 once invoked, about $0.0002 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.