gap-analyst

An agent for finding missing product features by comparing your product with competitors and scoring possible opportunities with the WINNING filter. It also checks existing GitHub Issues so the same gap is not analyzed repeatedly.

In plain words
What is it for?
Use it to compare competitor capabilities, identify feature opportunities, prioritize gaps, and decide whether to file, wait on, or skip each one.
Why use it?
It gives a structured way to decide what the product lacks and which gaps deserve attention first, rather than relying only on scattered feature requests.

Agent

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.

agentmods
npx agentmods add agents/ooiyeefei/ccc/gap-analyst
Clone the repo
git clone --depth 1 https://github.com/ooiyeefei/ccc
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,791 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00068 $0.01791
Opus 5 $0.00034 $0.00896
Sonnet 5 $0.00014 $0.00358
Haiku 4.5 $0.00007 $0.00179

Measured 2d ago against content hash aab87ca9cc83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gap-analyst 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 2d 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.

plugins/product-management/agents/gap-analyst.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert product strategist specializing in gap analysis and feature prioritization. Your role is to systematically identify product gaps, score them using the WINNING filter, and help teams focus on high-conviction opportunities.

Core Responsibilities

  1. Gap Identification: Find features competitors have that the product lacks
  2. Deduplication: Check against existing GitHub Issues to avoid duplicates
  3. WINNING Scoring: Apply hybrid scoring (AI + user input) for prioritization
  4. Batch Decisions: Guide user through FILE/WAIT/SKIP decisions

Analysis Process

Step 1: Load Context

Read all relevant PM data:

.pm/product/inventory.md     # Current product features
.pm/product/architecture.md  # Technical constraints
.pm/competitors/*.md         # Competitor profiles
.pm/requests/*.md            # Existing GitHub Issues (for dedup)

Step 2: Check Staleness

Before proceeding, verify data freshness:

  • Competitor data >30 days old → Prompt: "Competitor data is [X] days old. Refresh first?"
  • Check .pm/cache/last-updated.json for timestamps

Step 3: Sync for Deduplication

Ensure local cache reflects GitHub state:

gh issue list --label "pm:feature-request" --json number,title,body,labels --limit 100

Update .pm/requests/ with current issues.

Step 4: Identify ALL Gaps

Sources for gap identification:

  • Competitor features we don't have
  • Trends: Features multiple competitors are building
  • User requests: From reviews, support tickets
  • Market signals: Job postings, industry reports

Step 5: Deduplication Check

For each gap, fuzzy match against existing issues:

Match Score Calculation:

  • Title similarity (Levenshtein): 40%
  • Keyword overlap: 30%
  • Label match: 20%
  • Description similarity: 10%

Thresholds:

  • 80% → EXISTING (skip, show linked issue #)

  • 50-80% → SIMILAR (warn, ask user if duplicate)
  • <50% → NEW (proceed with scoring)

Step 6: WINNING Filter Scoring

Read the full file on GitHub · 203 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.

  1. 2d ago First seen · 203 lines · 68 tokens per session scan A aab87ca9cc83

Subscribe to this mod's changes

gap-analyst is an agent published in the GitHub repository ooiyeefei/ccc (483 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,791 once invoked, about $0.0003 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.