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 Szotasz/marveen --skill post-rollback-diagnosegit clone --depth 1 https://github.com/Szotasz/marveenWrote 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/szotasz/marveen/post-rollback-diagnose)<a href="https://agentmods.dev/skills/szotasz/marveen/post-rollback-diagnose"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/post-rollback-diagnose/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/szotasz/marveen/post-rollback-diagnose"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/post-rollback-diagnose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 20 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00053 | $0.00771 |
| Opus 5 | $0.00026 | $0.00385 |
| Sonnet 5 | $0.00011 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
post-rollback-diagnose 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 11d 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.
What it actually says
[Operator-kezdeményezett feladat a dashboardról: sikertelen frissítés diagnózisa]
A legutóbbi frissítés elbukott, és a rendszer automatikusan visszaállt a korábbi, működő verzióra. A box MOST a régi, működő verzión fut, tehát NINCS sürgősség. Nyugodtan, körültekintően dolgozz. A felhasználó a dashboardon explicit kérte ezt a diagnózist (Claude kredit jóváhagyva).
Cél: derítsd ki, MIÉRT bukott a frissítés, és ha biztonságosan javítható, javítsd.
Ha van backend/dev al-ügynököd, delegáld neki a diagnózist és a javítást, majd ellenőrizd; ha nincs, végezd el magad.
Diagnózis források (olvasd ELŐSZÖR):
{{INSTALL_DIR}}/store/update.log-- a bukás konkrét oka (a legutóbbi futás a fájl végén){{INSTALL_DIR}}/store/update.last-result-- a rögzített kimenet (status, phase, message)git status,git log @{u}..HEAD,git log --oneline -10
KÖTELEZŐ guardrailek (SOHA ne szegd meg):
- SOHA ne
git push --force/-f. Force-push tilos. - SOHA ne dobj el helyi változást. Ha a working tree piszkos:
git stash(NEMgit checkout/reset --harda helyi munkára). A stash-t hagyd meg, ne dropold. - A frissítés/rollback maga a robusztus
update.shdolga. NE írj párhuzamos update- vagy rollback-logikát; a diagnózisod arról szóljon, miért bukott, és a javítás a gyökér-okot célozza (pl. package-lock szinkron, node ABI, build-hiba, divergált history). - Ha kódot módosítasz a javításhoz: előbb LOKÁLISAN
npm run build, majd győződj meg róla, hogy a build zöld, MIELŐTT bármit késznek jelentesz. Ne indítsd újra magadtól a szolgáltatást éles környezetben; a következő frissítés/restart úgyis ezt teszi. - Ha divergált history a gyökér-ok (a helyi checkout előrébb van az upstreamnél): NE reszeteld erőszakkal. Írd le pontosan, mely helyi commitok vannak (
git log @{u}..HEAD), és kérd az operatőr döntését, mielőtt bármit átrendezel.
Amikor kész vagy (akár javítottad, akár csak diagnózis): jelentsd az eredményt röviden -- a gyökér-ok, mit tettél (vagy mit javasolsz), és hogy a build zöld-e. A box közben végig a működő régi verzión maradt.
What ships with it
1 file 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.
- 11d ago First seen · 27 lines · 53 tokens per session scan A c7a58a217225
post-rollback-diagnose is a skill published in the GitHub repository Szotasz/marveen (98 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 771 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 2026-08-30.
Other skills, from other repositories
oma-observability
Intent-based observability + traceability router across layers, boundaries, and signals. Routes to vendor-specific skills via category taxonomy; owns transport tuning, meta-observability, incident forensics. Use for observability, traceability, telemetry, APM, RUM, metrics, logs, traces, profiles, SLO, incident…
oma-debug
Bug diagnosis and fixing specialist - analyzes errors, identifies root causes, provides fixes, and writes regression tests. Use for bug, debug, error, crash, traceback, exception, and regression work.
log-troubleshooting
Investigate and troubleshoot daemon logs at /.comis/logs/. Covers NDJSON log format, Pino level codes, field dictionary, and staged analysis strategies for efficient troubleshooting of large log files. Use this skill whenever the user asks about logs, errors, warnings, daemon issues, slow operations, debugging daemon…
debugging
Systematic root cause analysis — find the cause before fixing.
verification
Reproduce bugs, validate fixes, and run regressions.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.