Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/openshift-eng/ai-helpersnpx agentmods add skills/openshift-eng/ai-helpers/reevaluate-job-runsWrote 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/openshift-eng/ai-helpers/reevaluate-job-runs)<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/reevaluate-job-runs"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/reevaluate-job-runs/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/skills/openshift-eng/ai-helpers/reevaluate-job-runs"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/reevaluate-job-runs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.02512 |
| Opus 5.5 | $0.00011 | $0.01005 |
| Sonnet 5.5 | $0.00006 | $0.00502 |
| Haiku 4.5 | $0.00003 | $0.00251 |
Grade A, and why
reevaluate-job-runs scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
that inspect API JSON also use `jq` and `curl`. How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reevaluate Job Runs
Sippy Symptoms recognize known conditions in OpenShift CI artifacts. A symptom
selects artifact files with a glob and uses a string, regex, or file
(existence) matcher. A match applies one or more Labels: stable,
human-readable tags such as ImagePullNeverCompletes that appear in Sippy, Spyglass, and
triage workflows.
Symptom detection normally runs automatically as new job artifacts arrive. Reevaluation asks Sippy to scan completed runs with the current symptom definitions, which is useful when a symptom was created or changed after those runs completed.
When to Use This Skill
Use this skill to:
- Preview which symptoms and labels match existing runs without writing.
- Apply a new or updated symptom to older completed runs.
- Re-scan every job run behind a Component Readiness regression or triage.
Prerequisites
Authentication to the sippy-auth API requires a Bearer token from the DPCR
OpenShift cluster (https://api.cr.j7t7.p1.openshiftapps.com:6443). Use the
oc-auth skill to select the correct context. Export the token rather than
putting it in the process list:
DPCR_CONTEXT="dpcr-context-name"
SIPPY_TOKEN="$(oc whoami -t --context="$DPCR_CONTEXT")"
export SIPPY_TOKEN
test -n "$SIPPY_TOKEN"
The implementation uses Python 3 and the standard library only. The examples
that inspect API JSON also use jq and curl.
Preview and Apply
--dry-run uses the same asynchronous API and artifact scan as an applied
reevaluation, but reports the labels without changing BigQuery, GCS, or
PostgreSQL:
JOB="periodic-ci-example-job"
BUILD_ID="1856789012345678848"
PROW_URL="https://prow.ci.openshift.org/view/gs/test-platform-results-public/logs/$JOB/$BUILD_ID"
python3 plugins/ci/skills/reevaluate-job-runs/reevaluate_job_runs.py \
"$PROW_URL" --dry-run --format summary
After reviewing the preview, omit --dry-run to apply the current symptom
set:
python3 plugins/ci/skills/reevaluate-job-runs/reevaluate_job_runs.py \
1856789012345678848 1856789012345678849 --format summary
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.
- 12d ago Changed · +68 lines 9ccddd211d6e
- 1mo ago Changed ad438a47ada6
- 1mo ago First seen · 166 lines · 28 tokens per session scan A c66a074bc261
reevaluate-job-runs is a skill published in the GitHub repository openshift-eng/ai-helpers (119 stars, last pushed yesterday), licensed Apache-2.0. It adds 28 tokens to every session and 2,512 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…