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 ScottRBK/forgetful --skill forgetful-recallgit clone --depth 1 https://github.com/ScottRBK/forgetfulWrote 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/scottrbk/forgetful/forgetful-recall)<a href="https://agentmods.dev/skills/scottrbk/forgetful/forgetful-recall"><img src="https://agentmods.dev/badge/skills/scottrbk/forgetful/forgetful-recall/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/scottrbk/forgetful/forgetful-recall"><img src="https://agentmods.dev/badge/skills/scottrbk/forgetful/forgetful-recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.00950 |
| Opus 5.5 | $0.00031 | $0.00380 |
| Sonnet 5.5 | $0.00016 | $0.00190 |
| Haiku 4.5 | $0.00008 | $0.00095 |
Grade A, and why
forgetful-recall 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recalling knowledge from Forgetful
Retrieval quality is decided by how the query is shaped and scoped, and by treating coverage as something to judge rather than assume. Recall before proposing; history usually exists.
Invoking operations
Operations are named by registry name (query_memory, get_recent_memories, ...). Invoke
via whichever surface this agent has:
- MCP:
execute_forgetful_tool(tool_name="query_memory", arguments={...}) - CLI:
forgetful call query_memory --args '{"query": "..."}' --json
Get any operation's schema at runtime: how_to_use_forgetful_tool (MCP) or
forgetful tools info <operation> (CLI) — schemas are deliberately not repeated here.
Step 1 — Shape the query
query_context is a required parameter alongside query; the call errors without it.
The vector search embeds query alone. When cross-encoder reranking runs, it also uses
query_context to refine the ranking. Include exact identifiers in query when they
matter, but search does not guarantee literal matches.
Done when: both query and query_context are written, not just a bare keyword.
Step 2 — Scope deliberately
Reads are cross-project by default, and usually should stay that way — knowledge transfers.
Narrow with project_ids when the task is project-bound; add strict_project_filter=True
to also keep linked memories inside those projects (the default False lets links cross
them). Use importance_threshold to cut noise — it excludes anything scored below the value
given, pairing naturally with forgetful-remember's rubric, where 5 is the noise floor for
bulk/automated captures. Adjust k to trade breadth for focus. These are filters layered on
top of semantic search, which stays the primary retrieval mechanism throughout.
Done when: the scope is a choice, not a default accident.
Step 3 — Judge coverage
Results are budgeted (about 8000 tokens / 20 memories), so assess coverage rather than non-emptiness:
truncated: true→ narrow the query (raise the threshold, scope the project) instead of accepting silent loss.- A miss on the first angle → re-query from a different facet (the feature area, the technology, the error text) before concluding the knowledge doesn't exist.
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 Changed · -1 lines 3071ec3a0f99
- 1mo ago First seen · 94 lines · 78 tokens per session scan A f21b771e8f88
forgetful-recall is a skill published in the GitHub repository ScottRBK/forgetful (340 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 950 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
semantic-search
Zero-dependency TF-IDF search across MUSE memory, roles, and skills. Use when user wants to find information across their project context.
recall
Fan-out search across all memory sources when context is unclear or vaguely referenced. Triggers on: 'from earlier', 'remember when', 'what we discussed', 'that thing with', 'the conversation about', 'did we ever', 'what happened with', 'you mentioned', 'we talked about', 'earlier today', 'last session', 'the other…
use-verifiable-memory
Research and synthesize from a local Verifiable Memory Bank with source-backed evidence, reproducible selectors, chronology, attribution, and explicit uncertainty. Use when a request asks Codex to recall banked material, investigate a topic, verify a claim, build a dossier or timeline, distinguish quoted facts from…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
screenpipe
Search screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.
memory-retain
Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.