[detection-analysis] Detection Analysis Report — 2026-09-02

[github-actions[bot]]

Summary

• Window evaluated: last 24 full hours (UTC), covering runs from 2026-09-02T11:19Z to 2026-09-02T22:56Z
• Total runs analyzed: 237
• Detection-enabled runs: 237 (100%)
• Regular runs (gh-aw-detection: false): 0 (0%)
• Misconfigured workflows found: 0

Note

No workflows in this window explicitly disable the gh-aw-detection feature, and no detection job failures were found. All 237 runs across 82 workflows ran with threat detection enabled (the default).

Comparison Chart

Because no runs opted out of detection this window, the "Regular Runs" bars are 0 across the board — this is a true reading of the data, not a gap in collection. Detection-enabled runs finished at an 87.76% success rate with an average of 206,016 tokens per run.

Misconfigured Workflows

No misconfigured workflows detected in this window.

View All Run Metrics

Workflow	Total Runs	Detection Runs	Regular Runs	Success Rate	Avg Tokens	Engine(s)
PR Sous Chef	44	44	0	100.0%	440,799	pi
Issue Monster	21	21	0	100.0%	119,992	codex
Test Quality Sentinel	13	13	0	100.0%	10,125	copilot
PR Code Quality Reviewer	12	12	0	100.0%	821,635	copilot
AI Moderator	11	11	0	81.82%	109,456	codex
Impeccable Skills Reviewer	11	11	0	100.0%	22,099	copilot
Matt Pocock Skills Reviewer	11	11	0	100.0%	23,630	copilot
Ponytail Reviewer	11	11	0	100.0%	241,539	codex
Design Decision Gate 🏗️	9	9	0	100.0%	183,171	pi
Avenger	8	8	0	0.0%	0	codex
Daily Go Test Parallelizer	6	6	0	83.33%	80,227	codex
Auto-Triage Issues	4	4	0	100.0%	58,491	pi
Contribution Check	3	3	0	100.0%	21,653	copilot
Code Scanning Fixer	2	2	0	0.0%	11,465	copilot
Deep Report	2	2	0	100.0%	125,762	claude
PR Triage Agent	2	2	0	100.0%	71,070	copilot
[aw] Failure Investigator (6h)	2	2	0	100.0%	9,401	claude
Agent Performance Analyzer - Meta-Orchestrator	1	1	0	100.0%	32,788	copilot
Agent Persona Explorer	1	1	0	100.0%	488,816	pi
Agentic Workflow AIC Usage Optimizer	1	1	0	100.0%	24,893	copilot
Agentic Workflow Audit Agent	1	1	0	0.0%	0	codex
Architecture Guardian	1	1	0	100.0%	6,057	copilot
Blog Auditor	1	1	0	100.0%	16,244	claude
Bot Detection	1	1	0	0.0%	0	codex
Breaking Change Checker	1	1	0	0.0%	0	copilot
CI Optimization Coach	1	1	0	100.0%	31,232	copilot
CLI Consistency Checker	1	1	0	100.0%	14,141	copilot
Claude Code User Documentation Review	1	1	0	100.0%	99,124	claude
Constraint Solving — Problem of the Day	1	1	0	100.0%	8,145	copilot
Copilot Agent PR Analysis	1	1	0	0.0%	0	claude
Copilot PR Prompt Pattern Analysis	1	1	0	100.0%	15,993	copilot
Daily AIC Consumption Report (Sentry + Grafana OTel)	1	1	0	100.0%	0	goose
Daily AWF Spec Compiler Surfacing Review	1	1	0	100.0%	854,266	pi
Daily Agent of the Day Blog Writer	1	1	0	100.0%	17,217	copilot
Daily Agentic Workflow AIC Usage Audit	1	1	0	100.0%	20,434	copilot
Daily Ambient Context Optimizer	1	1	0	100.0%	28,714	copilot
Daily BYOK Ollama Test	1	1	0	0.0%	0	copilot
Daily CLI Performance Agent	1	1	0	100.0%	189,369	pi
Daily Cache Strategy Analyzer	1	1	0	100.0%	713,099	pi
Daily Caveman Optimizer	1	1	0	100.0%	20,291	claude
Daily Choice Type Test	1	1	0	100.0%	7,830	claude
Daily Code Debt Cleanup — Aider	1	1	0	0.0%	0	aider
Daily Code Metrics and Trend Tracking Agent	1	1	0	0.0%	0	crush
Daily Copilot PR Merged Report	1	1	0	100.0%	15,178	copilot
Daily Credit Limit Test	1	1	0	100.0%	187,651	codex
Daily Fact	1	1	0	0.0%	0	pi
Daily Formal Spec Verifier	1	1	0	100.0%	29,692	copilot
Daily Go Function Namer	1	1	0	100.0%	143,752	pi
Daily Go Test Stubs — Aider	1	1	0	0.0%	0	aider
Daily Graft Intelligence	1	1	0	100.0%	11,457	copilot
Daily Issues Report Generator	1	1	0	100.0%	23,111	copilot
Daily Malicious Code Scan Agent	1	1	0	100.0%	14,690	copilot
Daily Max Ai Credits Test	1	1	0	0.0%	14,763	codex
Daily Project Performance Summary Generator (Using MCP Scripts)	1	1	0	0.0%	549,012	pi
Daily Regulatory Report Generator	1	1	0	0.0%	0	codex
Daily Reliability Review	1	1	0	100.0%	0	opencode
Daily SPDD Spec Planner	1	1	0	100.0%	15,785	copilot
Daily Safe Output Integrator	1	1	0	100.0%	30,587	copilot
Daily Safe Output Tool Optimizer	1	1	0	100.0%	72,322	claude
Daily Secrets Analysis Agent	1	1	0	100.0%	14,195	copilot
Daily Security Observability Report	1	1	0	100.0%	37,971	copilot
Daily Spec Coverage Review	1	1	0	100.0%	7,080	copilot
Daily Team Evolution Insights	1	1	0	100.0%	0	goose
Dead Code Removal Agent	1	1	0	0.0%	17,117	copilot
Delight	1	1	0	100.0%	22,068	copilot
Duplicate Code Detector	1	1	0	0.0%	0	codex
ESLint Monster	1	1	0	100.0%	36,590	pi
GitHub MCP Structural Analysis	1	1	0	100.0%	31,353	claude
Issue Triage Agent	1	1	0	100.0%	740,173	codex
Linter Miner	1	1	0	0.0%	38,179	copilot
Lockfile Statistics Analysis Agent	1	1	0	100.0%	28,203	claude
Package Specification Enforcer	1	1	0	100.0%	259,234	pi
Package Specification Librarian	1	1	0	100.0%	38,396	copilot
PureLock	1	1	0	0.0%	1,336,091	codex
Repository Quality Improvement Agent	1	1	0	100.0%	22,389	copilot
Slide Deck Maintainer	1	1	0	100.0%	16,814	copilot
Squad Game Planner	1	1	0	100.0%	30,236	copilot
Team Status	1	1	0	100.0%	8,795	copilot
The Daily Repository Chronicle	1	1	0	100.0%	1,511,943	pi
Typist - Go Type Analysis	1	1	0	100.0%	167,854	claude
UK AI Operational Resilience	1	1	0	100.0%	22,146	copilot
Workflow Normalizer	1	1	0	100.0%	1,607,905	codex

View Historical Trend

Detection-run success rate has held in the 78–92% band over the last ~4 recorded snapshots, with today's 87.76% at the higher end. Regular-run counts have been at or near zero since 2026-09-01, consistent with detection being enabled fleet-wide.

Recommendations

• No detection-configuration fixes are needed this window — keep monitoring for any workflow that newly adds gh-aw-detection: false, since the runbook's rule-1 threshold (>3 runs/7 days while disabled) would flag it going forward.
• Outside the scope of detection misconfiguration, two workflows show sustained failure patterns worth a look by their owners:
  • Avenger — 0% success rate across all 8 runs this window (agent job fails every time, 0 tokens consumed), e.g. run §33624861220. Detection itself succeeds, so this looks like an unrelated agent-side issue (config, credentials, or a broken trigger), not a detection misconfiguration.
  • Code Scanning Fixer — 0% success rate across 2 runs, e.g. run §33632778572.
• Continue the daily trend snapshot so a real "flip" to gh-aw-detection: false on a high-traffic workflow (rule 1) or an alternating configuration (rule 3) is caught early.

References:

• §33624861220 — Avenger, repeated agent-job failure
• §33632778572 — Code Scanning Fixer, failure
• §33626194781 — AI Moderator, failure (detection job itself succeeded)

Warning

Firewall blocked 1 domain

The following domain was blocked by the firewall during workflow execution:

• api.anthropic.com

To allow these domains, add them to the network.allowed list in your workflow frontmatter:

network:
  allowed:
    - defaults
    - "api.anthropic.com"

See Network Configuration for more information.

Generated by 🔎 Detection Analysis Report · claude · agent · 168.2 AIC · ⌖ 10.2 AIC · ⊞ 9K · ◷

• expires on Sep 5, 2026, 3:34 PM UTC-08:00