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.
git clone --depth 1 https://github.com/maxkle1nz/m1ndnpx agentmods add skills/maxkle1nz/m1nd/m1nd-firstWrote 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.
[](https://agentmods.dev/skills/maxkle1nz/m1nd/m1nd-first)<a href="https://agentmods.dev/skills/maxkle1nz/m1nd/m1nd-first"><img src="https://agentmods.dev/badge/skills/maxkle1nz/m1nd/m1nd-first.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
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.
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 | $0.00078 | $0.11701 |
| Opus 5 | $0.00039 | $0.05851 |
| Sonnet 5 | $0.00016 | $0.02340 |
| Haiku 4.5 | $0.00008 | $0.01170 |
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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 734 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.
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, onenext_move, andhonest_gapsinto a single packet before you read or edit anything. If it returnsneeds_ingest(empty/unbound graph), do not call genericingest: 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-northonly after the human has run it. Meanwhile use the isolatedm1nd agent ... --repoCLI path for investigation, or the exact authority flow plusexternal_mutation_servicefor a governed existing-brain mutation. - Before
rg, shell globbing, or manual file reads,m1ndanswers 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 anorth/seek/impactpass first. - Prefer the cheapest
m1ndsurface that preserves truth:- exact text ->
search - path pattern ->
glob - known purpose, unknown location ->
seek - topic, subsystem, or connected neighborhood ->
activate - unfamiliar repo orientation ->
north(orauditwhen you only want the structural map) - stacktrace or runtime error text ->
trace
- exact text ->
- 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_AVAILABLEunless an exact typed consumer and authority receipt are present. - Before risky edits or change reviews, pass through
impact,validate_plan, and usuallysurgical_context_v2. - Keep
agent_idstable across one investigation unless intentionally splitting roles.
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.
- 8d ago First seen · 734 lines · 78 tokens per session scan A 53f12c6dcc11
m1nd-first is a skill published in the GitHub repository maxkle1nz/m1nd (22 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 11,701 once invoked, about $0.0004 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.
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.
trace-mcp
Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.
trace-mcp-refactoring
Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.
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…
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.
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.