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 agentmods add skills/gebruder/wirken/json-toolsnpx skills add gebruder/wirken --skill json-toolsgit clone --depth 1 https://github.com/gebruder/wirkenWrote 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/gebruder/wirken/json-tools)<a href="https://agentmods.dev/skills/gebruder/wirken/json-tools"><img src="https://agentmods.dev/badge/skills/gebruder/wirken/json-tools.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.00351 |
| Opus 5 | $0.00005 | $0.00176 |
| Sonnet 5 | $0.00002 | $0.00070 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
json-tools 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 5d 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
JSON Tools
Parse and transform JSON using jq.
Query
- Pretty print:
echo '<json>' | jq . - Get field:
echo '<json>' | jq '.field' - Nested field:
echo '<json>' | jq '.a.b.c' - Array element:
echo '<json>' | jq '.[0]' - Array length:
echo '<json>' | jq 'length'
Filter and transform
- Select fields:
echo '<json>' | jq '{name: .name, id: .id}' - Filter array:
echo '<json>' | jq '.[] | select(.status == "active")' - Map:
echo '<json>' | jq '[.[] | .name]' - Sort:
echo '<json>' | jq 'sort_by(.date)' - Group:
echo '<json>' | jq 'group_by(.type)' - Unique:
echo '<json>' | jq '[.[].category] | unique'
File operations
- Read and query:
jq '.key' file.json - Compact:
jq -c . file.json - Raw strings (no quotes):
jq -r '.name' file.json - Convert to CSV:
jq -r '.[] | [.name, .value] | @csv' file.json
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.
- 5d ago First seen · 45 lines · 11 tokens per session scan A 6a3ffb7a74c0
json-tools is a skill published in the GitHub repository gebruder/wirken (170 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 351 once invoked, about $0.0001 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
council
Run 8-persona Council validation on a feature/ADR, then auto-create a Linear ticket if score >= 8/10.
decompose
Decompose a MEGA ticket into component-scoped sub-issues on Linear, with dependency DAG and parallel execution plan.
generate-backlog
Scan codebase to generate MEGA backlog tickets (20-40 pts each). Maintains 400+ pts stock on Linear.
sync-plan
Cycle-aware bidirectional sync between plan.md and Linear. Discovers all cycle tickets, detects drift, updates markers.
fill-cycle
Analyze cycle capacity gap and propose backlog items to fill the sprint to 80% of proven velocity.
pr-guardian
STOA PR Guardian — advisory three-axis review (ADR compliance, security, AI code smell) with binary GO/NO-GO verdict + confidence. Never approves, never blocks merge.