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 GerritCodeReview/gerrit-mcp-server --skill gerrit-task-querygit clone --depth 1 https://github.com/GerritCodeReview/gerrit-mcp-serverWrote 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/gerritcodereview/gerrit-mcp-server/gerrit-task-query)<a href="https://agentmods.dev/skills/gerritcodereview/gerrit-mcp-server/gerrit-task-query"><img src="https://agentmods.dev/badge/skills/gerritcodereview/gerrit-mcp-server/gerrit-task-query/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/gerritcodereview/gerrit-mcp-server/gerrit-task-query"><img src="https://agentmods.dev/badge/skills/gerritcodereview/gerrit-mcp-server/gerrit-task-query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 Prompt Injection · line 108 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 111 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 114 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00064 | $0.01465 |
| Opus 5.5 | $0.00026 | $0.00586 |
| Sonnet 5.5 | $0.00013 | $0.00293 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
gerrit-task-query 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gerrit Task Query
The Gerrit task plugin attaches a task tree to each change. Tasks represent CI checks, review requirements, and dependency gates. This skill shows how to fetch the task tree, find tasks that need action, and determine what to do.
The tools get_task_tree and get_actionable_tasks are provided by the
gerrit_mcp_server_task extension (entry point gerrit_mcp_server.extensions).
They are available whenever gerrit-mcp-server is running with the task
extension installed and a configured Gerrit host that has the task plugin
enabled.
1. Fetch tasks for a change
Task plugin options (task--applicable, task--only, etc.) are Gerrit
DynamicOptions — they are passed as direct HTTP query parameters
(&task--applicable), not as standard Gerrit output options (&o=).
Using the MCP tools (preferred — returns structured task tree JSON):
# All applicable tasks for a change
get_task_tree(change_id="123")
# Scope to one root task
get_task_tree(change_id="123", task_only="Jenkins")
# Convenience: returns only READY and FAIL nodes, pre-walked
get_actionable_tasks(change_id="123")
get_actionable_tasks(change_id="123", task_only="Jenkins")
Using query_changes / get_change_details (plain-text summary only):
# These pass task parameters but only return a text summary — use the task tools above instead
query_changes(query="change:123", parameters={"task--applicable": None})
get_change_details(change_id="123", parameters={"task--applicable": None})
2. Task node fields
| Field | Meaning |
|---|---|
name |
Task name |
status |
Status value (see table below) |
hint |
Human-readable explanation (present on READY and FAIL) |
in_progress |
true if task is currently executing |
has_pass |
true if the task has a terminal pass/fail condition |
exported |
Custom key-value metadata from the task definition |
change |
Change number — only on tasks generated by a change-type tasks-factory |
sub_tasks |
Child task nodes (recursive, arbitrary depth) |
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 · 128 lines · 64 tokens per session scan A b5dd6b5e8f6e
gerrit-task-query is a skill published in the GitHub repository GerritCodeReview/gerrit-mcp-server (21 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 1,465 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.
Other skills, from other repositories
bump-version
Bump the Logic-Lens version across all six metadata locations at once (package.json, the four plugin manifests, and the README badge), then validate. Use when cutting a release or when npm run validate reports a version mismatch.
signals-scout-pr-follow-up
Follow-up Signals scout for recently merged pull requests. Works out whether each one has deployed, then checks the project's telemetry for whether it did what it claimed, had the impact it expected, or caused a side effect that needs a look.
swarm-pi-review
Review a Git working tree or branch with read-only Pi workers. Use standard for bugs, security, regressions, and missing tests; use lean for diff-bound simplification, deletion, reuse, YAGNI, or native replacements. Route one question to ask and broader risk analysis to orchestrate.
signals-scout-skills-store
Skill-hygiene scout for the team's PostHog skills store. Watches recently-changed and most- used skills for authoring violations — vague descriptions, bloated bodies, dead file links, kitchen-sink scope, committed secrets.
turning-engineering-analytics-into-insights
Converts engineering analytics (PR / CI) data into saved PostHog insights, dashboards, and subscriptions, and explains how to query the product data directly with SQL. Covers discovering per-team GitHub warehouse tables via engineering-analytics-sources, replicating curated column semantics in HogQL, reading exposed…
managing-endpoint-versions
Work safely with endpoint versions — preview a draft in the playground, roll back to an older version, update settings on one version without bumping query history, deactivate a specific version. Use when the user asks "how do I roll back my endpoint", "preview my changes before publishing", "I want to fix v5 without…