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 skills add Razaib-khan/ForgeWeave --skill memory-managergit clone --depth 1 https://github.com/Razaib-khan/ForgeWeaveWrote 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/razaib-khan/forgeweave/memory-manager)<a href="https://agentmods.dev/skills/razaib-khan/forgeweave/memory-manager"><img src="https://agentmods.dev/badge/skills/razaib-khan/forgeweave/memory-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/razaib-khan/forgeweave/memory-manager"><img src="https://agentmods.dev/badge/skills/razaib-khan/forgeweave/memory-manager.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00017 | $0.00540 |
| Opus 5.5 | $0.00007 | $0.00216 |
| Sonnet 5.5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
Memory 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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Manager
Purpose
Persist and retrieve structured data across sessions — research outputs, intermediate reasoning steps, reusable knowledge chunks, and cache entries. Prevents redundant work by reusing previously computed results when inputs match.
When to Use
- Research results should be saved for future reference
- Intermediate reasoning needs to be persisted for multi-step workflows
- Previously computed results can be reused instead of recomputed
- Debug or trace information needs to be logged
When Not to Use
- The data is ephemeral and only needed for the current response
- The data contains secrets or credentials (use secure storage instead)
- The storage would exceed reasonable size limits
Inputs
| Input | Type | Required | Description |
|---|---|---|---|
operation |
enum | Yes | save, load, search, clear |
key |
string | Depends | Unique key for the data |
data |
object | For save | The data to persist |
namespace |
string | No (default: general) | Category for the data |
Expected Outputs
| Output | Description |
|---|---|
| Operation result | Success with location, or loaded data, or search results |
Exact Workflow Steps
- Determine the persistence location based on namespace and TUI
- For save: serialize data to disk at
research/or.<tui>/memory/ - For load: deserialize data from its persisted location
- For search: scan persisted data for matching keys or content
- For clear: remove caches and temporary data
Required Checks
- Saved data is retrievable with the correct key
- Cache entries have expiration or size limits
- No sensitive data is persisted without warning
Failure Modes
| Failure Condition | Response |
|---|---|
| Key not found on load | Report "not found" |
| Storage full | Suggest clearing old entries |
| Serialization fails | Report the unsupported type |
References
| Reference | Path |
|---|---|
| Cache & Store skill | ../cache-store/SKILL.md |
| research/ directory | ./research/ |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 80 lines · 17 tokens per session scan A ebd31bdf9537
Memory Manager is a skill published in the GitHub repository Razaib-khan/ForgeWeave (1 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 540 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
squads-learn
Capture learnings after completing work. Use when finishing a task, fixing a bug, discovering a pattern, or learning something worth remembering for future sessions. Helps build institutional memory.
context-search
A continuity workflow for finding context from earlier coding-agent sessions. It can inspect continuation notes and session records when a task refers to previous work.
auto-why
A decision-tracing workflow that searches project documents such as Lore, specifications, and architecture notes. It looks for the recorded reason behind a design or implementation choice.
island
A discrete, loadable brain.
sync
Pull and push your brain.
c-memory
Persistent memory across Claude Code sessions — remember facts, preferences, and context.