Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add davistroy/claude-marketplace/plugin install personal-pluginWrote 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/davistroy/claude-marketplace/task-sync)<a href="https://agentmods.dev/skills/davistroy/claude-marketplace/task-sync"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/task-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.
<a href="https://agentmods.dev/skills/davistroy/claude-marketplace/task-sync"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/task-sync.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00169 | $0.05040 |
| Opus 5.5 | $0.00068 | $0.02016 |
| Sonnet 5.5 | $0.00034 | $0.01008 |
| Haiku 4.5 | $0.00017 | $0.00504 |
Grade A, and why
task-sync scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Sync
Local-first task tracking backed by a canonical tasks.json (with a generated,
read-only TASKS.md view) that optionally reconciles with GitHub or Gitea
issues. All logic lives in the bundled task_sync Python tool — this skill's
job is invocation, table rendering, and human-in-the-loop decisions (conflict
resolution, confidentiality review, the public-repo push warning). The tool
never auto-resolves a conflict and never pushes anything without an explicit
plan the user has seen.
Setup
The tool is bundled at tools/task-sync/src. Resolve the plugin root the same
way other bundled-tool skills do, then invoke every subcommand through
python3 -m task_sync:
PLUGIN_DIR="${CLAUDE_PLUGIN_ROOT:-$(find ~ -path '*/plugins/personal-plugin' -type d 2>/dev/null | head -1)}"
TOOL_SRC="$PLUGIN_DIR/tools/task-sync/src"
PYTHONPATH="$TOOL_SRC" python3 -m task_sync status
tasks.json lives at the target repo's root by default (--tasks tasks.json,
resolved relative to the working directory). Pass --tasks <path> for any
other location.
Version-skew preflight
Run this once, before the first subcommand, and report the result if it warns:
python3 - "$PLUGIN_DIR" <<'PY'
import json, os, re, sys
served = re.search(r"/personal-plugin/(\d+\.\d+\.\d+)(?:/|$)", sys.argv[1])
served = served.group(1) if served else None
reg = os.path.expanduser("~/.claude/plugins/installed_plugins.json")
try:
entries = json.load(open(reg))["plugins"]["personal-plugin@troys-plugins"]
installed = entries[0]["version"]
except Exception:
installed = None
if served and installed and served != installed:
print(f"WARNING: this session is serving personal-plugin {served}; "
f"{installed} is installed. Run /reload-plugins to pick it up "
f"(a full restart also works). "
f"Until then this skill body may be older than the bundled tool.")
else:
print(f"version-skew: none ({served or 'unknown'})")
PY
Why this exists. A running Claude Code session serves the plugin version it
resolved at start-up. claude plugin update writes installed_plugins.json and
prints "Restart to apply changes", but it does not change what the current
session is already serving. So a long-lived session can run the current
bundled tool from repo source while reading a stale skill body — a current
tool against an old contract, with no error anywhere. That is #232: a session
served an 11.3.0 body whose plan-JSON key list predated orphans, so the orphan
findings the tool emitted were never read.
What ships with it
4 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.
- 1mo ago First seen · 419 lines · 169 tokens per session scan A 1b36cb61c773
task-sync is a skill published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 18d ago), licensed MIT. It adds 169 tokens to every session and 5,040 once invoked, about $0.0007 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 2026-09-04.
Other skills, from other repositories
antfu-issue-triage
Triage open issues and PRs of the current GitHub repo - find already-fixed, duplicate, and spam items, suggest labels, gauge demand from reactions and comments, then present a table of proposed actions and comments for confirmation before touching anything. Use when asked to triage, organize, clean up, or groom issues…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…