What is find-duplicates?

A workflow that uses semantic similarity to find issues describing the same or closely related problem; pgvector is a database extension for searching numeric text representations.

Use it when creating issues, checking suspected duplicates, or cleaning the backlog by comparing issue titles and descriptions within a project.

It helps prevent duplicate issues from filling the backlog when the wording differs but the underlying problem is similar.

find-duplicates — Skill for Claude Code and Codex by pilotspace

Install

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.

Any agent

npx skills add pilotspace/pilot-space --skill find-duplicates

Clone the repo

git clone --depth 1 https://github.com/pilotspace/pilot-space

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pilotspace/pilot-space/find-duplicates/github.svg)](https://agentmods.dev/skills/pilotspace/pilot-space/find-duplicates)

Your own site

<a href="https://agentmods.dev/skills/pilotspace/pilot-space/find-duplicates"><img src="https://agentmods.dev/badge/skills/pilotspace/pilot-space/find-duplicates/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pilotspace/pilot-space/find-duplicates"><img src="https://agentmods.dev/badge/skills/pilotspace/pilot-space/find-duplicates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,571 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.01571
Opus 5.5	$0.00006	$0.00628
Sonnet 5.5	$0.00003	$0.00314
Haiku 4.5	$0.00002	$0.00157

Measured 2mo ago against content hash 2270afb6d4a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

find-duplicates 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 2mo 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.

backend/src/pilot_space/ai/templates/skills/find-duplicates/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Find Duplicates Skill

Detect potential duplicate issues using semantic similarity search with pgvector embeddings.

Quick Start

Use this skill when:

New issue being created (automatic check)
User suspects duplicate exists (/find-duplicates)
Cleaning up issue backlog

Example:

New issue: "Users cannot log in with email addresses"

AI finds duplicates:
- "Login fails for email users" (similarity: 0.92, RECOMMENDED duplicate)
- "Email authentication broken" (similarity: 0.88, RECOMMENDED duplicate)
- "User auth not working" (similarity: 0.65, ALTERNATIVE - may be related)

Workflow

Generate Embedding
- Combine issue title + description
- Generate embedding using OpenAI text-embedding-3-large (3072 dims)
- Store in embeddings column (pgvector)
Semantic Search
- Query pgvector for similar issues using cosine similarity
- Filter by project_id (same project)
- Exclude closed/archived issues (optional)
- Return top 10 matches
Score Similarity
- RECOMMENDED duplicate (>0.85): Very high semantic overlap
- DEFAULT duplicate (0.70-0.85): Likely duplicate, needs review
- ALTERNATIVE related (0.60-0.70): Possibly related, not duplicate
Provide Context
- Include issue status (open, in_progress, closed)
- Show creation date (older = likely original)
- Link to issue for review

Output Format

{
  "duplicates": [
    {
      "issue_id": "issue-abc123",
      "title": "Login fails for email users",
      "similarity": 0.92,
      "confidence": "RECOMMENDED",
      "status": "open",
      "created_at": "2024-01-15T10:00:00Z",
      "rationale": "Very high semantic similarity (0.92), same symptoms described",
      "url": "/issues/issue-abc123"
    },
    {
      "issue_id": "issue-def456",
      "title": "Email authentication broken",
      "similarity": 0.88,
      "confidence": "RECOMMENDED",
      "status": "in_progress",
      "created_at": "2024-01-20T14:30:00Z",
      "rationale": "High similarity, currently being worked on",
      "url": "/issues/issue-def456"
    },
    {
      "issue_id": "issue-ghi789",
      "title": "User auth not working",
      "similarity": 0.65,
      "confidence": "ALTERNATIVE",
      "status": "closed",
      "created_at": "2023-12-10T09:15:00Z",
      "rationale": "Moderate similarity, may be related but different root cause",
      "url": "/issues/issue-ghi789"
    }
  ],
  "summary": "Found 3 potential duplicates (2 RECOMMENDED)",
  "suggestion": "Review issue-abc123 before creating new issue"
}

Read the full file on GitHub · 227 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.

2mo ago First seen · 227 lines · 15 tokens per session scan A 2270afb6d4a2

Subscribe to this mod's changes

find-duplicates is a skill published in the GitHub repository pilotspace/pilot-space (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,571 once invoked, about $0.0001 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 2026-08-31.

Project management

story-readiness

Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.

Donchitos/Claude-Code-Game-Studios · 48 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

ring:mapping-feature-relationships

Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…

LerianStudio/ring · 104 tokens

remove

Remove a deployed framework or addon from the current workspace.

jmagly/aiwg · 12 tokens

qa-project-bootstrap

Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…

petrkindlmann/qa-skills · 124 tokens