Agent skill

Blindspot Pass

by jellydn in jellydn/my-ai-tools

Inspect history and architecture for hidden constraints before risky cross-cutting changes.

MITAuto-check: notes

Install Blindspot Pass

skills CLI
$ npx skills add jellydn/my-ai-tools --skill blindspot-pass -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jellydn/my-ai-tools blindspot-pass --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jellydn/my-ai-tools.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/blindspot-pass .claude/skills/blindspot-pass && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
blindspot-pass
GitHub stars
123
Token cost
~1.7k tokens
SKILL.md length
401 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
MIT

At a glance

Inspect history and architecture for hidden constraints before risky cross-cutting changes.

  • Works in 5 steps: Define Scope → Search for Context → Identify Gotchas → …
  • SKILL.md covers When to Use, What It Does, How to Execute and Example Usage, plus 4 more sections
  • Calls git and rg

What it does

Blindspot Pass is an agent skill from jellydn/my-ai-tools. Inspect history and architecture for hidden constraints before risky cross-cutting changes.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: cline, claude, opencode, amp, codex, gemini, cursor, pi

The repository describes itself as: Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, OpenCode, Amp, Li, Codex and Claude Code Switch with custom… The licence is MIT.

Example prompts

  • “/blindspot-pass”

Requirements

  • Compatibility (from SKILL.md): cline, claude, opencode, amp, codex, gemini, cursor, pi

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Define Scope
  2. Search for Context
  3. Identify Gotchas
  4. Surface Questions
  5. Present Findings

What it can do on your machine

Read from SKILL.md and the folder at commit 62c9227. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • rg

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    cline, claude, opencode, amp, codex, gemini, cursor, pi

    From compatibility in the SKILL.md frontmatter.

Context cost

Blindspot Pass loads about 1.7k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 401 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:108
    egration tests use test credentials from .env.test
  • NoteMentions a .env fileSKILL.md:148
    e test mode uses different API keys from .env.stripe.test

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jellydn/my-ai-tools at commit 62c9227, republished under its MIT licence (© jellydn). 401 words, ~1,653 tokens.

Download SKILL.mdSave it as .claude/skills/blindspot-pass/SKILL.md (or your agent's skills folder).
name
blindspot-pass
description
Inspect history and architecture for hidden constraints before risky cross-cutting changes.
compatibility
cline, claude, opencode, amp, codex, gemini, cursor, pi
license
MIT
hint
Use before starting complex or unfamiliar work to identify hidden issues
user-invocable
true

Blind Spot Pass

When to Use

Use this skill before starting implementation when:

  • Working on an unfamiliar part of the codebase
  • Integrating with systems you don't fully understand
  • The task has high stakes or complexity
  • You sense there might be hidden gotchas

What It Does

A blind spot pass helps identify unknown unknowns that could derail implementation or lead to poor architectural decisions.

How to Execute

Step 1: Define Scope

Clearly state what you're about to work on:

  • Feature or change description
  • Affected modules/systems
  • Current understanding level
Step 2: Search for Context

Look in multiple places for relevant history:

bash
# Recent changes to related files
git log --oneline --all -20 -- path/to/module/

# Search commit messages for keywords
git log --all --grep="auth\|oauth\|provider" --oneline

# Find related discussions in code comments
rg -i "TODO|FIXME|HACK|XXX" path/to/module/

# Search for error handling patterns
rg "catch|throw|error" path/to/module/ -A 3
Step 3: Identify Gotchas

Document findings in categories:

Technical Gotchas:

  • Edge cases in existing code
  • Performance considerations
  • Error handling patterns
  • Testing requirements

Architectural Gotchas:

  • Existing abstractions to follow
  • Integration points
  • Data flow patterns
  • State management approaches

Business Gotchas:

  • Implicit requirements from past discussions
  • Feature flags or phased rollouts
  • Backward compatibility needs
  • Security or compliance requirements
Step 4: Surface Questions

Generate questions that would change the approach:

  • "I see error handling uses X pattern; should I follow it?"
  • "There's a feature flag system; does this need one?"
  • "Previous auth work had Y consideration; does that apply here?"
Step 5: Present Findings

Format as a structured report:

markdown
## Blind Spot Analysis: [Task Name]

### Context Sources Checked
- [x] Git history (last 3 months, 45 commits in auth/)
- [x] Code comments and TODOs (found 3 relevant)
- [x] Error handling patterns (uses Result type)
- [x] Test coverage (integration tests in /tests/auth/)

### Key Findings

**Architectural Patterns**:
- All auth providers extend BaseOAuthProvider
- Must implement 3 lifecycle hooks: init, authenticate, refresh
- Config validation happens at provider registration

**Known Gotchas**:
- GitHub OAuth requires app installation per org (not per user)
- Refresh tokens expire after 6 months of inactivity
- Rate limiting uses Redis; need to handle connection failures

**Testing Requirements**:
- Mock responses in tests/fixtures/oauth/
- Integration tests use test credentials from .env.test
- Must test token refresh flow explicitly

### Questions Before Proceeding

1. Should GitHub provider support org-level installation?
2. How should we handle rate limit failures? (retry? user error?)
3. Is there a preferred library for GitHub OAuth, or implement from scratch?

### Recommended Approach

[Brief recommendation based on findings]

Example Usage

User: "I need to add Stripe payment integration to our checkout flow"

Agent: "Let me do a blind spot pass first to identify unknowns."

[Agent searches codebase, git history, finds existing payment integrations]

Agent: "Blind Spot Analysis: Stripe Integration

Context Sources Checked:
- Git history: Found previous PayPal integration (6 months ago)
- Existing code: Braintree integration in /payments/providers/
- Tests: Payment integration tests use VCR for API mocking

Key Findings:

Architectural Patterns:
- All payment providers implement PaymentProvider interface
- Webhook handling is centralized in /webhooks/payment-events
- PCI compliance: Never store card numbers, only Stripe tokens

Known Gotchas:
- Must implement idempotency keys for all charge operations
- Webhook signature verification required (security requirement)
- Stripe test mode uses different API keys from .env.stripe.test
- Currency handling: Store amounts as integers (cents) not floats

Testing Requirements:
- Use Stripe test fixtures (don't call real API in tests)
- Must test webhook verification with valid and invalid signatures
- Cover 3 main flows: successful charge, declined card, network error

Questions Before Proceeding:

1. Should we support Stripe Connect (for marketplaces) or just direct charges?
2. Do we need recurring billing support, or one-time payments only?
3. Should failed charges retry automatically, or require user action?
4. What currency/currencies do we need to support?

Recommended Approach:
Based on the PayPal integration pattern, implement as a plugin in
/payments/providers/stripe/ with webhook handler in /webhooks/stripe/.
Follow idempotency pattern from Braintree integration.
"

Best Practices

  1. Search broadly first: Git history, code, comments, tests, documentation
  2. Look for patterns: What did previous similar work do?
  3. Find the gotchas: Search for error handling, TODOs, FIXMEs
  4. Generate good questions: Focus on architecture-changing decisions
  5. Provide recommendations: Synthesize findings into an approach
Show full SKILL.md (147 more words)Show less

Integration with Other Skills

  • Before: Define task scope
  • After Blind Spot Pass: Run interview skill if major unknowns remain
  • During Implementation: Use implementation-logger to track deviations
  • After Implementation: Use quiz-me to verify understanding

Common Pitfalls

  • Too narrow: Only checking files you'll edit (check dependencies too)
  • Too shallow: Only reading current code (check git history for context)
  • No questions: Findings without questions don't guide next steps
  • No synthesis: Raw data dump instead of actionable recommendations

Success Criteria

A good blind spot pass:

  • Reports only evidence-backed gotchas; zero gotchas is valid when inspection finds none
  • Generates questions only when their answers could change the approach
  • Records each finding's outcome: changed approach, resolved, or not reproduced
  • References concrete evidence (commits, code, comments)
  • Provides a clear recommendation for how to proceed
  • Stops when the relevant boundaries and implementation-changing unknowns are covered, rather than optimizing for a fixed time or finding count

© jellydn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/blindspot-pass of jellydn/my-ai-tools.

Open the folder on GitHubat commit 62c9227

Compare with similar skills

Blindspot Pass next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Blindspot Pass compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Blindspot Pass this skilljellydn/my-ai-tools123—~1.7kAutomated safety check: NotesMIT
Node Inspect Debuggeropenclaw/openclaw392k1 repos~894Automated safety check: PassMIT
Blender Motion State Inspectionaffaan-m/ECC277k1 repos~2kAutomated safety check: PassMIT
Wobbling Ty Constraint Orderastral-sh/ruff50k—~838Automated safety check: PassMIT
Constraint-Driven Developmentaddyosmani/agent-skills105k2 repos~5.2kAutomated safety check: PassMIT
Historyalsk1992/CloddsBot3k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Node Inspect Debugger

    openclaw/openclaw

    Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.

    392k GitHub starsUsed in 1 repo~894 tokens
    Frontend & DesignAuto-check passed
  • A skill your agent uses when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where screenshots alone are not enough.

    277k GitHub starsUsed in 1 repo~2k tokens
    Game DevelopmentAuto-check passed
  • Official

    A skill your agent uses when a user asks to wobble ty constraint ordering, check constraint-set or TDD ordering determinism, test reversed constraint/typevar IDs, or investigate nondeterministic ty…

    50k GitHub stars~838 tokensUpdated today
    Testing & QAAuto-check passed
  • Constraint-Driven Development

    addyosmani/agent-skills

    Records a project's quality bar in CONSTRAINTS.md and watches diffs for signs an agent quietly weakened it, such as suppressions, skipped tests or lowered thresholds.

    105k GitHub starsUsed in 2 repos~5.2k tokens
    DevelopmentAuto-check passed
  • History

    alsk1992/CloddsBot

    Trade history tracking, sync, and performance analytics. An agent skill from alsk1992/CloddsBot.

    3k GitHub stars~1.6k tokensUpdated 8 days ago
    Auto-check passed
  • Blindspot Pass

    Neeeophytee/finding-unknowns-skills

    Surface the user's unknown unknowns before work starts. An agent skill from Neeeophytee/finding-unknowns-skills.

    344 GitHub stars~482 tokensUpdated 13 days ago
    Auto-check passed

More from jellydn/my-ai-tools

All 33 skills in this repo
  • Babysit PR

    jellydn/my-ai-tools

    A skill your agent uses when monitoring an open GitHub PR for CI failures, review feedback, mergeability, and safe retries or fixes.

    123 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed
  • Visual PR

    jellydn/my-ai-tools

    Posts a concise visual outline as a GitHub pull request comment.

    123 GitHub stars~764 tokensUpdated yesterday
    Auto-check passed
  • Qmd Knowledge

    jellydn/my-ai-tools

    Manage project knowledge with qmd — captures learnings, decisions, and conventions

    123 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Prd

    jellydn/my-ai-tools

    Generate Product Requirements Documents from feature ideas — plans specs and requirements

    123 GitHub starsUsed in 4 repos~1.8k tokens
    Auto-check passed
  • Capability Experiments

    jellydn/my-ai-tools

    Build an interactive report or experiment when the user asks to explore model capabilities.

    123 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • PR Review

    jellydn/my-ai-tools

    Fix PR review comments by implementing requested changes. An agent skill from jellydn/my-ai-tools.

    123 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

Questions about Blindspot Pass

What does Blindspot Pass do?

Inspect history and architecture for hidden constraints before risky cross-cutting changes. Blindspot Pass is an agent skill from jellydn/my-ai-tools. Inspect history and architecture for hidden constraints before risky cross-cutting changes.

How do I install Blindspot Pass in Claude Code?

Run `npx skills add jellydn/my-ai-tools --skill blindspot-pass -a claude-code`. Or copy the skill folder (skills/blindspot-pass in jellydn/my-ai-tools) into .claude/skills/blindspot-pass in your project. Claude Code loads it when a task matches its description.

How do I install Blindspot Pass in Codex?

Run `npx skills add jellydn/my-ai-tools --skill blindspot-pass -a codex`. Or copy the skill folder (skills/blindspot-pass in jellydn/my-ai-tools) into .agents/skills/blindspot-pass in your project. Codex loads it when a task matches its description.

Can I use Blindspot Pass in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jellydn/my-ai-tools --skill blindspot-pass -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/blindspot-pass, .gemini/skills/blindspot-pass, .github/skills/blindspot-pass and .opencode/skills/blindspot-pass in your project.

What does Blindspot Pass need to run?

Going by SKILL.md and its folder, Blindspot Pass needs the command-line tools its instructions call (git and rg). Compatibility (from SKILL.md): cline, claude, opencode, amp, codex, gemini, cursor, pi.

Does Blindspot Pass access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Blindspot Pass safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Blindspot Pass use?

Blindspot Pass is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Blindspot Pass use?

About 1.7k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Blindspot Pass?

Skills that share tags, products or a category with Blindspot Pass: Node Inspect Debugger (openclaw/openclaw, 392k stars), Blender Motion State Inspection (affaan-m/ECC, 277k stars), Wobbling Ty Constraint Order (astral-sh/ruff, 50k stars) and Constraint-Driven Development (addyosmani/agent-skills, 105k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Blindspot Pass?

jellydn (a GitHub user) maintains it in jellydn/my-ai-tools, which has 123 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 10, 2026.

Source: jellydn/my-ai-tools on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.