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 agents/forsonny/maker-framework/maker-cache-managergit clone --depth 1 https://github.com/forsonny/maker-frameworkWhat 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 | $0.00024 | $0.02983 |
| Opus 5 | $0.00012 | $0.01491 |
| Sonnet 5 | $0.00005 | $0.00597 |
| Haiku 4.5 | $0.00002 | $0.00298 |
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.
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:
- LOOKUP - Check if a similar task has a cached decomposition pattern
- STORE - Save a successful decomposition pattern for future reuse
- 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:
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.
- 2d ago First seen · 547 lines · 24 tokens per session scan A da9099e982dd
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.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.