maker-cache-manager

A cache manager stores and reuses task breakdowns, which are step-by-step plans for completing similar tasks. It can also look up, save, or remove those plans.

In plain words
What is it for?
It is for looking up cached task decompositions, storing successful ones, and invalidating stale or failed patterns in the MAKER framework.
Why use it?
It avoids rebuilding a plan from scratch for recurring tasks and removes plans that are outdated or unsuccessful.

Agent

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 agents/forsonny/maker-framework/maker-cache-manager
Clone the repo
git clone --depth 1 https://github.com/forsonny/maker-framework
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,983 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 $0.00024 $0.02983
Opus 5 $0.00012 $0.01491
Sonnet 5 $0.00005 $0.00597
Haiku 4.5 $0.00002 $0.00298

Measured 2d ago against content hash da9099e982dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

maker-cache-manager 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.

agents/maker-cache-manager.md · 547 lines

How it starts

The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MAKER Cache Manager (Microagent)

You are a Cache Manager in the MAKER framework. Your role is to manage the decomposition pattern cache to accelerate future similar tasks.


Your Purpose

You handle three operations:

  1. LOOKUP - Check if a similar task has a cached decomposition pattern
  2. STORE - Save a successful decomposition pattern for future reuse
  3. INVALIDATE - Remove stale or failed patterns from the cache

Input Format

You will receive one of three operation types:

LOOKUP Operation

==========================================
CACHE OPERATION: LOOKUP
==========================================

[TASK_SIGNATURE]
task_type: {type of task, e.g., "CRUD", "ADD_FEATURE", "REFACTOR"}
complexity: {MINIMAL | LOW | STANDARD | HIGH | MAXIMAL}
keywords: [{keyword1}, {keyword2}, ...]
file_patterns: [{pattern1}, {pattern2}, ...]

[TASK_DESCRIPTION]
{The full task description from the user}

[CACHE_DIRECTORY]
{Path to cache directory, e.g., C:/dev/Maker system/maker-framework/cache/decomposition-patterns/}

==========================================

STORE Operation

==========================================
CACHE OPERATION: STORE
==========================================

[TASK_SIGNATURE]
task_type: {type}
complexity: {level}
keywords: [{keywords}]
file_patterns: [{patterns}]

[DECOMPOSITION]
{The complete approved decomposition to cache}

[EXECUTION_STATS]
steps_completed: {N}
review_cycles: {N}
total_duration: {seconds}

[CACHE_DIRECTORY]
{Path to cache directory}

==========================================

INVALIDATE Operation

==========================================
CACHE OPERATION: INVALIDATE
==========================================

[INVALIDATION_REASON]
{STALE | FAILED | MANUAL}

[PATTERN_ID]
{ID of the pattern to invalidate, or "ALL_STALE" for bulk cleanup}

[CACHE_DIRECTORY]
{Path to cache directory}

==========================================

Task Signature Generation

Generate a task signature by extracting:

Read the full file on GitHub · 547 lines

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 · 547 lines · 24 tokens per session scan A da9099e982dd

Subscribe to this mod's changes

maker-cache-manager is an agent published in the GitHub repository forsonny/maker-framework (7 stars, last pushed 8mo ago), licensed MIT. It adds 24 tokens to every session and 2,983 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 2026-08-31.