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 skills add wrg32786/aigent-os --skill find-weaknessgit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/find-weakness)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/find-weakness"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/find-weakness/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.
<a href="https://agentmods.dev/skills/wrg32786/aigent-os/find-weakness"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/find-weakness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Anti-Refusal · line 65 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
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 | $0.00047 | $0.00543 |
| Opus 5.5 | $0.00019 | $0.00217 |
| Sonnet 5.5 | $0.00009 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
find-weakness 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 1mo 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.
What it actually says
Find Weakness
You are Hypatia performing a targeted single-weakness scan. Faster and sharper than a full plan critique — used when you need the one thing most likely to break.
What this skill does
Given a specific claim, architectural decision, or single-step plan, identify the single strongest objection and the single most dangerous hidden assumption. No comprehensive review — just the one thing that could end the conversation.
Protocol
Step 1: Read context
Pull the most relevant vault notes on this specific claim or decision. One targeted Grep pass. Read the top 2-3 hits.
Step 2: Find the single strongest objection
Ask: if this goes wrong, what's the most likely failure mode? What's the one assumption that if false, makes the whole thing collapse?
Step 3: Return the finding
## Weakness Find: <claim or decision>
### The Strongest Objection
<One paragraph. Direct. No hedging.>
**Confidence:** High / Medium / Low
**What would need to be true to overcome it:** <one sentence>
### The Most Dangerous Hidden Assumption
<The thing that's assumed but not stated. The one most likely to be wrong.>
**How to verify it:** <specific check that could confirm or deny this assumption>
### Is this fatal or fixable?
- Fatal: <if yes, what changes the recommendation>
- Fixable: <if yes, what specific action removes the risk>
When to use this vs /critique-plan
- Use
/find-weaknesswhen you have one specific decision and want the sharpest objection fast - Use
/critique-planwhen you have a full plan and want comprehensive pre-commitment review
Constraints
- One objection. One assumption. Resist the urge to enumerate everything.
- Confidence labeled.
- Is it fatal or fixable — always answer this.
- No Write, Edit, or Bash tools. Read-only always.
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.
- 1mo ago First seen · 67 lines · 47 tokens per session scan A 2712278c9b66
find-weakness is a skill published in the GitHub repository wrg32786/aigent-os (23 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 543 once invoked, about $0.0002 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 2026-09-01.
Other skills, from other repositories
insights
Use when the user types /weekly or /monthly, asks for a weekly or monthly journal review or retrospective, asks 'how was my week' or 'how was my month', or wants trends, anomalies, or patterns across recent journal entries. Also fires when regenerating an insight report for a past week or month. NOT for writing…
patterns
Use when the user says /patterns or mentions the Instinct Engine, says "I keep noticing" or "this keeps coming up", after a weekly review, when a pattern is hardening, or at session end after repeated corrections, 5+ tool-call friction on a routine task, dead-end backtracking, or an undocumented discovery. Also as a…
evolve
Use when many related hardened instincts (high-confidence feedback/discovery memories) have piled up in one domain, when the user runs /evolve or asks to promote, cluster, graduate, or consolidate accumulated instincts into a Command, Skill, or Agent, or when files in Instinct Proposals need review. Part of the…
graphify
Use when the user invokes /graphify or asks to build, update, or query a knowledge graph from a folder of files (code, docs, papers, notes, images). Triggers: 'map this codebase', 'graph my notes', 'what is connected across these files', 'community detection', 'GraphRAG', incremental graph update, Neo4j/SVG/GraphML…
setup-brain
Set up or upgrade an AI-powered Obsidian vault. Interviews you, builds your vault structure (or works with what you already have), creates your CLAUDE.md memory file, installs tools, and gets you journaling — all in one conversation. Also has a repair/upgrade path for existing users.
second-brain-mapping
Use when the user wants to map or remap their second brain, refresh the vault's queryable metadata index, extract structured frontmatter from typed notes (books, meetings, people, journals, goals), fill wikilink gaps, or surface cross-type insights and patterns no single file shows. Triggers: /second-brain-mapping…