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 skills add Jarroslav/agentic-os --skill test-healgit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/skills/jarroslav/agentic-os/test-heal)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/test-heal"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/test-heal.svg" alt="Measured on agentmods" 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 | $0.00149 | $0.01283 |
| Opus 5 | $0.00075 | $0.00642 |
| Sonnet 5 | $0.00030 | $0.00257 |
| Haiku 4.5 | $0.00015 | $0.00128 |
Grade A, and why
test-heal 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 7d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
test-heal
Called by sdlc-engine Phase 10 (autonomous mode) when gate-runner fails on
test-side causes. Heal and re-run are deliberately separate responsibilities:
this skill edits and commits, gate-runner re-runs — a healer that re-runs its
own work can mask its own failures.
Methodology owner. How flake causes are isolated and classified is defined by the
flaky-debuggingblueprint inagentic-qe(skills/qe-blueprints/references/catalog/execute/flaky-debugging.md). This skill executes; the blueprint is the authority on method. If the two ever disagree, the blueprint wins and this file is what gets corrected — one source of truth, so two agents cannot follow two different sets of practices.
Inputs
run_dir— the active run directorygate_plan— the runner/commandsgate-runnerdetected (never re-detect here)failures— the failing tests with output excerpts fromqa-report.mdbranch— the active feature branch (all edits stay on it)
Step 1 — Triage every failure
Classify each failure by OWNERSHIP. When the test-failure-triage agent
already ran, map its cause classes onto this taxonomy instead of re-triaging:
TIMING / SELECTOR / DATA / ASSERTION-LOGIC / SHARED-STATE → test_issue
(or flaky for single-occurrence timing), ENV → environment_issue,
PROPAGATION or a genuine regression → application_issue.
| Class | Signals | Allowed action |
|---|---|---|
test_issue |
selector not found on unchanged UI, assertion against stale copy/fixture, order-dependent state, hard-coded wait too short | Fix the test (targeted edits at the cited file:line) |
environment_issue |
missing env var, service not running, port conflict, missing browser binary | No code edit — report the environment remediation |
flaky |
passes in isolation / fails in batch, timing-dependent, single occurrence | Stabilize the test (deterministic waits, isolation), never .skip |
application_issue |
test is right, behavior is wrong: real regression, 5xx from own code | Never touch — return it to the pipeline as a fix-up implementation task |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 108 lines · 149 tokens per session scan A e60c7c0cbdcd
test-heal is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 149 tokens to every session and 1,283 once invoked, about $0.0007 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.