agentmods.dev

m1nd-first

m1nd-first is a skill for Claude Code from maxkle1nz/m1nd. It costs 78 tokens per session (11,976 once invoked), scanned A, original, MIT.

A repository-investigation method that makes an `m1nd` knowledge graph the first place to look for context, prior work, and likely next steps. A repository is the project's files and history; a knowledge graph stores related information and connections.

In plain words
What is it for?
Use it when investigating code, searching for an implementation, reviewing changes, following specifications or documentation, or preparing a risky code change. It also defines what to do when no `m1nd` knowledge graph exists.
Why use it?
It helps avoid starting investigations with broad file searches when the repository's stored context can narrow the work first.

Skill for Claude Code

Written for Claude Code: SubagentStop hook event. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/mcp_agent_smoke.py --repo . --handshake-only --json.

not rated 23repo +2 changed 10d ago A scan SkillSpector: warn 78 tokens original MIT

Good fit Use it when investigating code, searching for an implementation, reviewing changes, following specifications or documentation, or preparing a risky code change. It also defines what to do when no m1nd knowledge graph exists.

Compare 6 skills from other repositories ↓
View source ↗ maxkle1nz/m1nd m1nd.world
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/maxkle1nz/m1nd
agentmods
npx agentmods add skills/maxkle1nz/m1nd/m1nd-first

Made for: Claude Code.

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 m1nd-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/maxkle1nz/m1nd/m1nd-first/github.svg)](https://agentmods.dev/skills/maxkle1nz/m1nd/m1nd-first)
Your own site
<a href="https://agentmods.dev/skills/maxkle1nz/m1nd/m1nd-first"><img src="https://agentmods.dev/badge/skills/maxkle1nz/m1nd/m1nd-first/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 m1nd-first

Your own site · 80×15
<a href="https://agentmods.dev/skills/maxkle1nz/m1nd/m1nd-first"><img src="https://agentmods.dev/badge/skills/maxkle1nz/m1nd/m1nd-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,976 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: 3 findings, up to high

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 →

  • high Rogue Agent · line 553
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Excessive Agency · line 99
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Rogue Agent · line 513
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.11976
Opus 5.5 $0.00031 $0.04790
Sonnet 5.5 $0.00016 $0.02395
Haiku 4.5 $0.00008 $0.01198

Measured 10d ago against content hash 481d022a188f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

m1nd-first 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/m1nd-first/SKILL.md · 754 lines

How it starts

The opening of the file, as written. The whole thing — 754 lines — stays where its author put it; the contents beside it link to each section on GitHub.

m1nd-first

This is a doctrine, not a manual.

Published 1.6.5 startup boundary

With a matching 1.6.5 wrapper/native runtime, agent first-minute --repo <repo> can prepare only the exact launcher-granted repository in an external private cache when no covering owner is found. Source files remain inputs. Only when reusing the automatic isolated cache does the CLI refresh the declared root before retrieval. Attached-owner freshness follows the owner's own semantics; inspect its version, binding, and freshness separately. Direct stdio also requires that explicit workspace grant and an existing safe external runtime. See agent autonomy. The human-birth guidance below applies to shared-brain and legacy launchers outside that contract, or the recovery actually returned by the installed runtime. A prompt, tool path, or reception mismatch never grants bootstrap authority; generic replace/merge and the human-only ceremony remain unavailable to agents.

Rules

  • Start with m1nd. In an MCP session, the front door is one call: north(task) — it composes trust, task context, prior cross-session memory, a sufficiency signal, one next_move, and honest_gaps into a single packet before you read or edit anything. If it returns needs_ingest (empty/unbound graph), do not call generic ingest: that mutation surface is policy-disabled. Say the door out loud instead — a repo with no brain gets one from the HUMAN's one-time ceremony, m1nd init --birth <repo>: offer that command and stop, then re-north only after the human has run it. Meanwhile use the isolated m1nd agent ... --repo CLI path for investigation, or the exact authority flow plus external_mutation_service for a governed existing-brain mutation.
  • Before rg, shell globbing, or manual file reads, m1nd answers or narrows FIRST — that is the default, not a question you ask only when convenient. The one exception is the Skip Conditions below (exact file+lines already known, or pure compiler/runtime truth); everything else earns a north/seek/impact pass first.
  • Prefer the cheapest m1nd surface that preserves truth:
    • exact text -> search
    • path pattern -> glob
    • known purpose, unknown location -> seek
    • topic, subsystem, or connected neighborhood -> activate
    • unfamiliar repo orientation -> north (or audit when you only want the structural map)
    • stacktrace or runtime error text -> trace
  • For docs/specs/knowledge, do not advertise generic ingest adapters while the mutation route is policy-disabled. Read the supplied artifacts directly or use an owner-internal indexing path; label graph ingestion NOT_AVAILABLE unless an exact typed consumer and authority receipt are present.
  • Before risky edits or change reviews, pass through impact, validate_plan, and usually surgical_context_v2.
  • Keep agent_id stable across one investigation unless intentionally splitting roles.

Read the full file on GitHub · 754 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 Changed · +15 lines 481d022a188f
  2. 11d ago Changed · +5 lines 5f51cff44165
  3. 1mo ago First seen · 734 lines · 78 tokens per session scan A 53f12c6dcc11

Subscribe to this mod's changes

m1nd-first is a skill published in the GitHub repository maxkle1nz/m1nd (23 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 11,976 once invoked, about $0.0003 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.

Code reviewDebuggingai-agentscode-graphcode-intelligencedeveloper-toolsmcpmcp-server
Related

Other skills, from other repositories

qartez

Semantic code intelligence skill for qartez MCP. Use qartez tools for code exploration, impact analysis, and guarded refactors; treat built-in code-tool denials as routing signals and recover via qartez replacements.

kuberstar/qartez-mcp · 48 tokens

roam

Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…

Cranot/roam-code · 86 tokens

enola

Use Enola when investigating architecture, dependencies, blast radius, cross-repository relationships, structural regressions, or what a code change did to the system.

enola-labs/enola · 34 tokens

lsp-inspect

Full code quality audit for a file, package, or directory. Supports batch mode (directory walk with --top ranking), comparison mode (--diff for branch-only issues), severity calibration by blast radius, fix suggestions, and confidence tiers. Applies a check taxonomy (dead symbols, silent failures, error wrapping…

blackwell-systems/agent-lsp · 126 tokens

lsp-dead-code

Enumerate exported symbols in a file and surface those with zero references across the workspace. Use when auditing for dead code, cleaning up APIs, or checking which exports are safe to remove.

blackwell-systems/agent-lsp · 43 tokens

lsp-impact

Blast-radius analysis for a symbol or file — shows all callers, type supertypes/subtypes, and reference count before you change it. Use when refactoring, deleting, or changing the signature of any function, type, or method. Also accepts a file path to surface all exported-symbol impact in one shot.

blackwell-systems/agent-lsp · 67 tokens