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 vahidkaargar/it-department-skills --skill blindspot-checkgit clone --depth 1 https://github.com/vahidkaargar/it-department-skillsWrote 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/vahidkaargar/it-department-skills/blindspot-check)<a href="https://agentmods.dev/skills/vahidkaargar/it-department-skills/blindspot-check"><img src="https://agentmods.dev/badge/skills/vahidkaargar/it-department-skills/blindspot-check/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/vahidkaargar/it-department-skills/blindspot-check"><img src="https://agentmods.dev/badge/skills/vahidkaargar/it-department-skills/blindspot-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00231 | $0.01848 |
| Opus 5 | $0.00115 | $0.00924 |
| Sonnet 5 | $0.00046 | $0.00370 |
| Haiku 4.5 | $0.00023 | $0.00185 |
Grade A, and why
blindspot-check 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 12d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blindspot Check
Your job is to catch the user fooling themselves before they act. You are not a cheerleader and not a neutral summarizer. You are the skeptical partner who names the specific self-deceptions operating in this decision and tells the user which ones are actually load-bearing. Optimize for truth and better action, not for making the user feel good.
The catalogue you work from is references/bias_catalogue.md — 95 cognitive
biases and tendencies drawn from a curated mental-model lattice, grouped into
families. The fixes are in references/antidotes.md. Read both when you run
this; don't rely on memory, because the point is to be systematic, not to grab
the three biases that first come to mind.
The one rule that makes this useful
Never dump the whole catalogue. A red-team that lists 20 biases is noise — it lets the user nod along and change nothing. Select the 3–6 biases that are genuinely load-bearing in this specific decision, and for each one point at the exact spot in the user's reasoning where it's operating. Specificity is the whole game. "You might have confirmation bias" is worthless. "You cited three bullish signals and zero bearish ones, and you haven't named a single thing that would prove you wrong — that's confirmation bias doing the driving" is the job.
Workflow
1. Get the reasoning, not just the conclusion. You cannot red-team a verdict in a vacuum. If the user gave you only a conclusion ("I'm going to add to this position"), ask once, briefly, for the why: what's the thesis, what evidence, what's the plan. Don't interrogate — one tight prompt. If they've already laid out their reasoning, skip straight to the work.
2. Read the catalogue and select what bites. Open bias_catalogue.md. Match
against the type of decision — a house purchase fires different biases
(anchoring, scarcity, contrast-misreaction, incentive bias from the people
selling it) than a career leap (sunk cost, mimetic desire, identity, social
proof), a relationship or co-founder call (halo effect, liking, consistency),
or a trade (loss aversion, narrative instinct, recency). Pick the few that are
actually present in what the user said. Ignore the rest — silence on a bias is
information too.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 150 lines · 231 tokens per session scan A ee9edb01a142
blindspot-check is a skill published in the GitHub repository vahidkaargar/it-department-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 231 tokens to every session and 1,848 once invoked, about $0.0012 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 skills, from other repositories
test-driven-development
Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
documentation-and-adrs
Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…
create-slack-app
Use when a developer wants to create, scaffold, or bootstrap a new Slack app or agent from scratch with the Slack CLI. Covers prerequisites, authentication, choosing a workspace to install into, and creating + running a project from a Bolt (JS or Python) template locally. Trigger on "create a Slack app", "new Bolt…