v1.0.0
First downloadable release of ci-cd-failure-analyzer.
Description
A read-only agent that finds why a pipeline failed — the first real error, its category, the probable cause, a fix and a ready-to-file bug ticket — with every claim tied to a log line or a commit.
- 43 files
- Claude Code, or one of the bundled exports for Codex, ChatGPT or Cursor, Python 3.9 or later — the adapter uses the standard library only, GitLab CI or GitHub Actions read access, or a job log saved to a file
What is included
- Setup and usage guide
- 38 supporting files
- Licence, changelog and updates
Requirements
- Claude Code, or one of the bundled exports for Codex, ChatGPT or Cursor
- Python 3.9 or later — the adapter uses the standard library only
- GitLab CI or GitHub Actions read access, or a job log saved to a file
Version history
Good questions, straight answers.
Does it call the GitLab or GitHub API?+
It can, with a read-only token you configure; the live API path is implemented but not yet tested against a live forge, so the file mode is the proven one today.
Will it retry my jobs?+
No. Retrying a job or filing a ticket is listed for your approval; the agent itself only reads.
What about secrets in the logs?+
The adapter masks tokens, keys and passwords before the log reaches the model, and the shared output check refuses secret-like strings in the result.
Similar products
Prompt PackThe Debugging Prompt System
- Instant download
- A text editor
Structured prompts for reproducible bug diagnosis.
- Bug triage
- Root-cause prompts
$29.99
AI ToolkitTest Case Generator
- Instant download
- Claude Code, or one of the bundled exports for Codex, ChatGPT or Cursor
An agent that turns requirements into positive, negative and edge test scenarios whose expected results come from the spec — and proves which rules are still untested.
- Every expected result cites its spec rule; no source means an open question
- A rule-to-scenario matrix checked by `tools/coverage_matrix.py`: uncovered rules, missing negatives, duplicates
$29.99
AI ToolkitSprint Planning Agent
- Instant download
- Claude Code, or one of the bundled exports for Codex, ChatGPT or Cursor
An agent that proposes a sprint scope that fits the team's real capacity — in person-days, buffer kept, dependencies respected — and says exactly what was left out and why.
- Capacity is an input, never a guess: the agent refuses to invent availability
- Unit conversion shown: weeks or hours to person-days
$29.99
AI ToolkitRequirements Analysis Agent
- Instant download
- Claude Code, or one of the bundled exports for Codex, ChatGPT or Cursor
An agent that makes a specification testable: every requirement atomic and traced, every vague word, contradiction and gap turned into a precise question for the business owner, before a line of code is written.
- Ambiguity signals detected by `tools/req_lint.py` and confirmed by the agent
- Contradictions shown side by side with both sources
$29.99
AI ToolkitTechnical Documentation Generator
- Instant download
- Claude Code, or one of the bundled exports for Codex, ChatGPT or Cursor
An agent that writes README, API and architecture docs that match the code as it is, and lists line by line the existing docs that lie: dead paths, removed scripts, unused variables. Drafts only, never overwrites.
- Drift detected by `tools/doc_drift.py`: dead paths, removed scripts and make targets, unused env vars, each with doc:line
- Drafts written to the report folder; replacing a doc needs your approval
$29.99
AI ToolkitTechnical Debt Analyzer
- Instant download
- Claude Code, or one of the bundled exports for Codex, ChatGPT or Cursor
An agent that finds the debt that actually costs your team — files that change all the time, are big, untested and full of TODOs — ranks it with a visible formula and turns the top items into backlog entries.
- Hotspot ranking by `tools/hotspots.py`: churn × size, with markers and test presence
- A visible formula: impact × churn ÷ effort, with its inputs stated
$49.99
Cursor RulesProduction Telemetry and Live Debugging Rules
- Instant download
- A central log store you can query
Four Cursor rules and a diagnostic playbook for answering a question about running production code without shipping a deploy to find out.
- Zero-redeploy state inspection in Node.js, Python and Go — stacks on signal, pool counters, goroutine and task lists
- Log and span payloads carrying the five fields that make correlation possible at all
$29.99
AI ToolkitProject Health Monitor
- Instant download
- Claude Code, or one of the bundled exports for Codex, ChatGPT or Cursor
An agent that gives an early, evidence-based health signal — schedule, delivery, quality, scope — rated GREEN, AMBER or RED against thresholds you set, with the trend since last time and the corrective actions.
- Ratings computed by `tools/health_score.py` against explicit, configurable thresholds
- A missing indicator gives NOT_RATED, never a default green
$49.99