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 agentmods add agents/ooiyeefei/ccc/gap-analystgit clone --depth 1 https://github.com/ooiyeefei/cccWhat 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 | $0.00068 | $0.01791 |
| Opus 5 | $0.00034 | $0.00896 |
| Sonnet 5 | $0.00014 | $0.00358 |
| Haiku 4.5 | $0.00007 | $0.00179 |
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.
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
- Gap Identification: Find features competitors have that the product lacks
- Deduplication: Check against existing GitHub Issues to avoid duplicates
- WINNING Scoring: Apply hybrid scoring (AI + user input) for prioritization
- 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.jsonfor 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
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.
- 2d ago First seen · 203 lines · 68 tokens per session scan A aab87ca9cc83
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.