memory-jq

A set of jq patterns for changing selected fields in a JSON memory file. jq is a command-line tool for reading and editing JSON without loading the whole file.

In plain words
What is it for?
Use it to read or set fields, append items to arrays, increase counters, add entities, and update timestamps in JSON memory.
Why use it?
It makes small memory updates more efficient and reduces the need to rewrite or inspect an entire JSON file for every change.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/abilityai/abilities/memory-jq
Any agent
npx skills add Abilityai/abilities --skill memory-jq
Clone the repo
git clone --depth 1 https://github.com/Abilityai/abilities

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 557 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00557
Opus 5 $0.00007 $0.00279
Sonnet 5 $0.00003 $0.00111
Haiku 4.5 $0.00001 $0.00056

Measured 2d ago against content hash 7aa51f142d42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-jq 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 2d 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.

plugins/agent-dev/memory-templates/json-state/memory-jq/SKILL.md · 82 lines

What it actually says

Memory JQ

Efficiently update JSON memory fields without loading the entire file.

Arguments

$ARGUMENTS - Operation in format: <operation> <json-path> [value]

Operations:

  • set - Set a field value
  • append - Add to an array
  • increment - Increment a number
  • get - Read a field value

Common Patterns

Set a simple field

jq '.profile.name = "Value"' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json

Set with variable (use --arg)

jq --arg val "New Value" '.profile.name = $val' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json

Append to array

jq '.memory.key_facts += ["New fact to remember"]' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json

Update timestamp

jq '.metadata.last_updated = now | todate' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json

Increment counter

jq '.metadata.total_interactions += 1' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json

Add entity

jq '.entities += [{"type": "person", "name": "John", "relationship": "client"}]' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json

Update nested field

jq '.context.active_topics = ["topic1", "topic2"]' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json

Read a field (get operation)

jq '.profile.name' memory/memory_index.json

Read array length

jq '.memory.key_facts | length' memory/memory_index.json

Execution

  1. Parse the user's $ARGUMENTS to determine operation
  2. Construct the appropriate jq command
  3. Execute with atomic write (tmp file + mv)
  4. Report the change made

Safety

  • Always use tmp file pattern to avoid corruption
  • Validate JSON after write with jq '.' memory/memory_index.json
  • Report errors if jq fails
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. 2d ago First seen · 82 lines · 14 tokens per session scan A 7aa51f142d42

Subscribe to this mod's changes

memory-jq is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 14d ago), licensed MIT. It adds 14 tokens to every session and 557 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens