career-ops-ui: Skill for Claude Code

.claude/skills/parent-sync/SKILL.md

parent-sync is a skill for Claude Code from Fighter90/career-ops-ui. It costs 83 tokens per session (4,877 once invoked), scanned A, original, MIT.

A repeatable process for bringing changes from a newer release of the parent career-operations project into its web interface. A parent project is the upstream codebase that this project depends on or mirrors.

In plain words
What is it for?
Use it when updating the parent project, applying an audit-only fix release, or working from a parent release URL. It guides the update, scopes changes, ports fixes, updates documentation, and runs the required checks.
Why use it?
It prevents a partial update from leaving the web interface out of sync with the parent project. The process also covers documentation, tests, release checks, and parity verification.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

This is Fighter90/career-ops-ui's own configuration. It tells Claude Code how to work on career-ops-ui itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything career-ops-ui configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cp ../providers/telegram-channel.mjs /tmp/tc.before # snapshot.

Reuse

Borrowing it

Nothing to install: this file belongs to Fighter90/career-ops-ui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Fighter90/career-ops-ui/main/.claude/skills/parent-sync/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Fighter90/career-ops-ui

Made for: Claude Code.

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 parent-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/fighter90/career-ops-ui/parent-sync/github.svg)](https://agentmods.dev/skills/fighter90/career-ops-ui/parent-sync)
Your own site
<a href="https://agentmods.dev/skills/fighter90/career-ops-ui/parent-sync"><img src="https://agentmods.dev/badge/skills/fighter90/career-ops-ui/parent-sync/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 parent-sync

Your own site · 80×15
<a href="https://agentmods.dev/skills/fighter90/career-ops-ui/parent-sync"><img src="https://agentmods.dev/badge/skills/fighter90/career-ops-ui/parent-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,877 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 medium

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 →

  • medium Rogue Agent · line 173
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 $0.00083 $0.04877
Opus 5.5 $0.00033 $0.01951
Sonnet 5.5 $0.00017 $0.00975
Haiku 4.5 $0.00008 $0.00488

Measured 1mo ago against content hash 6ede5493d1cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

parent-sync 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 1mo 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.

.claude/skills/parent-sync/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

parent-sync — parity release pipeline

Proven across v1.119.0 (parent 1.19), v1.120.0 (1.20), v1.123.0 (1.21). Each phase below is a hard gate — do not skip, do not reorder. The parent repo (..) is READ-ONLY except the user-authorized git pull itself.

Also covers audit-driven patch releases (no parent delta — e.g. v1.134.1 validation-hardening from a full-project + all-locales audit). Skip Phases 1–2 (no pull, no provider port); Phases 3–7 apply UNCHANGED — QA prompt, docs ×17, site changelog resync, wiki, cross-surface verify are all still mandatory. The count that moves on a fix-only release is usually just the test count.

Phase 0 — Load the working context, then defend it

Do this before Phase 1, every time. It is three reads and one diff, and it is what stops a release from re-deciding things that were already decided.

  1. Read CONTEXT.md — the domain dictionary. It settles the vocabulary this pipeline argues about every release: source vs adapter (94 vs 89 — the five RU sources have no adapter), mirror vs relay, telegram vs telegram-channel. Using the wrong word here produces the wrong port.
  2. Read PROGRESS.md — in particular Abandoned approaches. Every entry there is a thing that was tried and failed in a previous release (blanket token sweeps, \b near non-Latin scripts, building the site mid-fan-out, asserting a marker on the overall verdict). Do not retry them.
  3. Read docs/adr/ — the standing decisions. 0001 keep both telegram sources · 0002 defend fork divergences · 0003 mirror vs relay · 0004 liveness tiers. If the delta touches what a record covers, the record decides, not this release.
  4. Diff the fork's divergences BEFORE merging anything (ADR-0002). A conflict is not your safety net: on 2026-09-21 upstream reverted the Cyrillic LOCATIONISH_RE and the merge carrying that revert produced zero conflicts.

Read the full file on GitHub · 289 lines

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. 1mo ago Changed · +59 lines 6ede5493d1cc
  2. 1mo ago First seen · 230 lines · 83 tokens per session scan A 8e4a0fa86770

Subscribe to this mod's changes

parent-sync is a skill published in the GitHub repository Fighter90/career-ops-ui (88 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 4,877 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

version-release

Choose and apply the correct semantic version bump for this repository. Use for every user-visible release, before merge when a change set should ship as patch, minor, or major, and whenever package/plugin/desktop version metadata must stay synchronized.

hoangsonww/Claude-Code-Agent-Monitor · 50 tokens

release-guard

Run release-readiness checks for this repository. Use when validating docs, scripts, verification coverage, and operational safety before merge or release.

hoangsonww/Claude-Code-Agent-Monitor · 31 tokens

pull-request

Use this whenever the user asks to "open a PR", "ship this", "create the pull request", "make a PR", or once a feature/fix is verified and ready to push. Full lifecycle: branch → commit (commitizen) → issue → draft PR → CI → ready → autonomous monitor loop (fix comments, resolve threads, iterate until CI green + zero…

pierreb-devkit/Node · 113 tokens

release-announcement

Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.

paperclipai/paperclip · 42 tokens

release

Fully automate a release with version-bump and childhood.

thedotmack/claude-mem · 13 tokens

release-notes

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

phuryn/pm-skills · 57 tokens