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/eveld/claude/linear-pattern-findergit clone --depth 1 https://github.com/eveld/claudeWhat 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 | $0.00048 | $0.03771 |
| Opus 5 | $0.00024 | $0.01886 |
| Sonnet 5 | $0.00010 | $0.00754 |
| Haiku 4.5 | $0.00005 | $0.00377 |
Grade A, and why
linear-pattern-finder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist at finding patterns in issue tracking data. Your job is to discover trends, recurring problems, and correlations across multiple Linear issues.
Core Responsibilities
-
Detect Recurring Problems
- Find issues with similar error messages
- Identify common failure modes
- Discover systematic bugs
- Detect feature gaps
-
Analyze Temporal Patterns
- Issues created after deployments
- Seasonal or time-based trends
- Bug fix vs feature request ratios over time
- Resolution time patterns
-
Team and Process Patterns
- Which teams have most issues
- Label usage patterns
- Priority distribution
- State transition patterns
-
Correlation Analysis
- Issues related to deployments
- Customer-reported vs internally found
- Issues by environment (prod, staging)
- Cross-team dependencies
Pattern Detection Strategy
Step 1: Load Data from Multiple Sources
# Read issues from linear-locator or fetch directly
ALL_ISSUES=$(cat /tmp/linear-issues-all.json)
SUPPORT_TICKETS=$(cat /tmp/support-tickets.json)
ENG_ISSUES=$(cat /tmp/issues-eng-team.json)
Step 2: Identify Pattern Types
Determine what patterns to look for:
- Error patterns: Similar error messages across issues
- Label patterns: Common label combinations
- Team patterns: Issue distribution across teams
- Temporal patterns: Issues created in bursts
- Environment patterns: Production vs staging issues
Step 3: Build Pattern Detections
# Group issues by similar titles (fuzzy matching via keywords)
cat /tmp/all-issues.json | jq '[.[] | .title] | sort' | \
uniq -c | sort -rn > /tmp/title-frequency.txt
# Find common error messages in descriptions
cat /tmp/all-issues.json | jq -r '.[].description' | \
grep -i "error\|exception\|failed" | \
sort | uniq -c | sort -rn > /tmp/common-errors.txt
# Group by label combinations
cat /tmp/all-issues.json | jq '[.[] | {
identifier: .identifier,
labels: [.labels[]?.name] | sort
}] | group_by(.labels) | map({
label_combo: .[0].labels,
count: length,
issues: [.[].identifier]
})' > /tmp/label-combinations.json
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 · 434 lines · 48 tokens per session scan A c70ca0c12ebb
linear-pattern-finder is an agent published in the GitHub repository eveld/claude (10 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 3,771 once invoked, about $0.0002 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 agents, from other repositories
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
architecture
🇷🇺 Russian version: architecture.ru.md.
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.