post-rollback-diagnose

post-rollback-diagnose is a skill for Claude Code, Codex from Szotasz/marveen. It costs 53 tokens per session (771 once invoked), scanned A, original, MIT.

An on-demand workflow for finding out why a software update failed after the system automatically returned to its previous working version. It examines update records, repository state, and the failed update’s result.

In plain words
What is it for?
Use it to inspect update logs, recorded failure details, Git history, and local changes, then safely apply a repair when the cause can be fixed.
Why use it?
It lets someone investigate a failed update without disturbing the version that is currently working. It also sets safeguards against force-pushing or discarding local changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect update logs, recorded failure details, Git history, and local changes, then safely apply a repair when the cause can be fixed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/szotasz/marveen/post-rollback-diagnose
Install

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.

Any agent
npx skills add Szotasz/marveen --skill post-rollback-diagnose
Clone the repo
git clone --depth 1 https://github.com/Szotasz/marveen

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for post-rollback-diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/szotasz/marveen/post-rollback-diagnose/github.svg)](https://agentmods.dev/skills/szotasz/marveen/post-rollback-diagnose)
Your own site
<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.

agentmods 80×15 button for post-rollback-diagnose

Your own site · 80×15
<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>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash c7a58a217225, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

seed-scheduled-tasks/post-rollback-diagnose/SKILL.md · 27 lines

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 (NEM git checkout/reset --hard a helyi munkára). A stash-t hagyd meg, ne dropold.
  • A frissítés/rollback maga a robusztus update.sh dolga. 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.

Files

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.

Changes

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.

  1. 11d ago First seen · 27 lines · 53 tokens per session scan A c7a58a217225

Subscribe to this mod's changes

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.