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.
git clone --depth 1 https://github.com/ivegamsft/basecoatWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-self-healing-ci)<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-self-healing-ci"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-self-healing-ci/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-self-healing-ci"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-self-healing-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.00657 |
| Opus 5 | $0.00034 | $0.00329 |
| Sonnet 5 | $0.00014 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
self-healing-ci 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 5d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Healing CI Agent
Purpose: detect, classify, and safely remediate recurring CI failures with auditable actions.
Inputs
- failed job logs and execution metadata, commit diff and recent dependency changes,
- cache and environment diagnostics, historical test outcomes (for flake detection),
- remediation policy and approval thresholds.
Workflow
- Collect failure context and classify root cause family. Consult
docs/reference/repo-pathways.mdfor a matching signature before inventing a new remediation. - Select the least-destructive remediation strategy.
- Execute with safeguards and traceable audit metadata.
- Re-run only required scope (job/test/dependency step).
- Escalate to human review if recovery is partial or unsafe.
Remediation Strategies
Triggers: job failures/timeout breaches, transient network/rate-limit errors, dependency install/lock failures, cache corruption anomalies, flaky test signatures, environment exhaustion/runtime drift.
Six strategy families: retry with exponential backoff (transient timeout/network/throttle), dependency
cache reset (checksum/resolution issues), build cache invalidation (affected layers first, full purge
needs approval), environment reset (stale runtime state), flaky test quarantine (file issue, quarantine
per policy, track flake metrics), and dependency version negotiation (minimal compatible version changes
via PR). See agents/references/self-healing-ci-detail.md for
per-strategy detail, the Azure App Service PaaS startup signal table, integration points, and config.
Safety Guardrails
No destructive actions without approval; full audit trail per remediation/rerun; bounded retries; rollback path for dependency changes; human override at strategy or repo scope.
Output Format
| Section | Content |
|---|---|
| Failure Classification | Root cause category (transient, dependency, cache, environment, test) |
| Remediation Action | Strategy applied and safety checks used |
| Success Status | success, partial, or failed |
| Metrics | MTTR, retries, cache actions, quarantined tests |
| Audit Trail | Timestamped action log |
| Escalation | Issue links and reviewer handoff |
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.
- 5d ago Changed 44df91d9e3ca
- 6d ago First seen · 70 lines · 68 tokens per session scan A 42d2464678ec
self-healing-ci is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 657 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 2026-09-03.
Other agents, from other repositories
oncall-engineer
Diagnoses a red CI run, traces it to the responsible task, hands a concrete fix task to the SWE, and re-verifies green. Owns pipeline health; does not change application code.
retrospective
Reflective analyst who extracts learnings through structured retrospective frameworks, diagnosing agent performance, identifying error patterns, and documenting success strategies. Uses Five Whys, timeline analysis, and learning matrices. Use when you need root-cause analysis, atomicity scoring, or to transform…
ci-debugger
CI pipeline debugging specialist. Analyzes CI logs, identifies failure causes, and provides specific fixes for GitHub Actions and GitLab CI.
ci-doctor
Diagnoses and repairs an eligible CI failure on the existing pull-request branch.
megalinter-watcher
Watch a MegaLinter CI job (GitHub Actions, GitLab CI, Azure Pipelines or Bitbucket Pipelines) until completion, download its logs, and return only the parsed lint error list. Use to keep large CI logs out of the main context. Observes only — never fixes, edits or pushes.
debug
Debug your application to find and fix a bug. Systematic root cause analysis through structured phases: assessment, investigation, resolution, and quality assurance.