agentmods.dev

memory-compact

memory-compact is a skill for Claude Code, Codex from sunil-goyal-1502/project-memory. It costs 6 tokens per session (446 once invoked), scanned A, original, MIT.

A tool for shrinking a project’s stored record of technical decisions by combining related entries, removing duplicates, and keeping newer decisions that replace older ones.

In plain words
What is it for?
Use it to review `.ai-memory/decisions.jsonl`, check its size, and produce a shorter set of project decisions while preserving categories, confidence, and unresolved items.
Why use it?
Decision records can grow large and repeat the same information. Compacting them makes the stored project context smaller and easier to maintain.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the project-memory plugin — 11 skills, 2 agents, 1 MCP server shipped together

not rated 8 4mo ago A scan 6 tokens original MIT
View the source file sunil-goyal-1502/project-memory
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/sunil-goyal-1502/project-memory/memory-compact
Any agent
npx skills add sunil-goyal-1502/project-memory --skill memory-compact
Clone the repo
git clone --depth 1 https://github.com/sunil-goyal-1502/project-memory

Made for: Claude Code, Codex.

Or install project-memory, the plugin that ships this one along with the rest of its 11 skills, 2 agents, 1 MCP server.

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 memory-compact

README.md
[![agentmods](https://agentmods.dev/badge/skills/sunil-goyal-1502/project-memory/memory-compact.svg)](https://agentmods.dev/skills/sunil-goyal-1502/project-memory/memory-compact)
Your own site
<a href="https://agentmods.dev/skills/sunil-goyal-1502/project-memory/memory-compact"><img src="https://agentmods.dev/badge/skills/sunil-goyal-1502/project-memory/memory-compact.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 446 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 $0.00006 $0.00446
Opus 5 $0.00003 $0.00223
Sonnet 5 $0.00001 $0.00089
Haiku 4.5 $0.00001 $0.00045

Measured 4d ago against content hash ceb7e050ff6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-compact 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 4d 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.

skills/memory-compact/SKILL.md · 46 lines

What it actually says

Compact Project Decisions

Reduce the size of the decision store by merging related decisions, removing superseded ones, and deduplicating.

Steps

  1. Read .ai-memory/decisions.jsonl and parse all decisions.

    • If fewer than 5 decisions, tell the user compaction isn't needed yet.

  2. Read .ai-memory/metadata.json and check the token count.

    • Report current count to user.

  3. Analyze decisions for compaction opportunities:

    Look for these patterns:

    • Duplicates: Decisions with essentially the same meaning (even if worded differently)
    • Superseded: A later decision that overrides an earlier one (e.g., "Using MySQL" then later "Switched to PostgreSQL" — keep only the latter)
    • Mergeable: Multiple decisions in the same category that can be combined into one (e.g., three naming conventions → one combined convention)

  4. Produce a compacted set of decisions:

    • For merged entries, use the oldest timestamp from the merged decisions
    • Preserve all categories
    • Keep confidence as the max of merged entries
    • Set source to "compacted"
    • Add a note in rationale about what was merged if helpful
    • Preserve any "unresolved" decisions unless they were clearly resolved by later decisions

  5. Show the proposed changes to the user:

    • Decisions to remove (with reason: duplicate/superseded)
    • Decisions to merge (showing before → after)
    • Ask user to confirm before applying

  6. Write the compacted decisions back to .ai-memory/decisions.jsonl (overwrite the file).

  7. Run sync to update tool-specific files:

    node -e "require('${CLAUDE_PLUGIN_ROOT}/scripts/sync-tools.js').syncAll(process.cwd())"

  8. Report results: Show before/after decision count and estimated token savings.

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. 4d ago First seen · 46 lines · 6 tokens per session scan A ceb7e050ff6a

Subscribe to this mod's changes

memory-compact is a skill published in the GitHub repository sunil-goyal-1502/project-memory (8 stars, last pushed 4mo ago), licensed MIT. It adds 6 tokens to every session and 446 once invoked, about $0.0000 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 2026-08-31.

Memory and context
Related

Other skills, from other repositories

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens