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 barockok/slaude --skill memorygit clone --depth 1 https://github.com/barockok/slaudeWrote 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/barockok/slaude/memory)<a href="https://agentmods.dev/skills/barockok/slaude/memory"><img src="https://agentmods.dev/badge/skills/barockok/slaude/memory/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/barockok/slaude/memory"><img src="https://agentmods.dev/badge/skills/barockok/slaude/memory.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 | $0.00021 | $0.01121 |
| Opus 5.5 | $0.00008 | $0.00448 |
| Sonnet 5.5 | $0.00004 | $0.00224 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
memory 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 today.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured memory (kb_memoize with a type)
Each page carries a type, a confidence (told or inferred), a source,
and optionally supersedes. kb_memoize fills the common frontmatter
(as_of today, source defaults to told by <speaker> on a profile).
Pass subject (the Slack user id) for any page about a person.
Where each kind lives
type |
target + slug |
Holds |
|---|---|---|
profile |
profile + profile |
only what the person said: name to use, register, ping preferences, quiet hours, mutes |
correction (about how to treat a person) |
profile + correction-<short-slug> |
what was corrected, by whom, when |
person-note |
mine + people/<userId> |
your working observations of how to work with someone; always inferred |
commitment |
mine + commitments/<short-slug> |
a promise you made |
investigation |
mine + investigations/<slug> |
symptom, hypotheses with status, evidence links, last touched |
correction (about your own work) |
mine + self/lessons |
a candidate lesson |
outcome |
mine + outcomes/<short-slug> |
an action you took and the signal afterwards |
lessons / heartbeat |
mine + self/lessons / self/heartbeat |
one page each, kept by later phases |
team-fact |
shared + shared/people/<userId> or shared/services/<name> (a convention, not enforced) |
ownership, who debugged what; raises an approval card |
Commitments
Write one the moment you promise. Fields (fields): promiser,
beneficiary, thread (<channel>:<threadTs>), due (a time or an event),
check (what to look at when it falls due), on_no_change
(close-in-one-line or silent), status (open, done, dropped). When it
is kept or abandoned, write a new page under a new slug (for example
commitments/<slug>-done) with status done or dropped and supersedes
naming the open one. The new page can never reuse the old slug.
Profile
target:"profile"takes onlyprofileandcorrectionpages, and a profile page uses the slugprofile.- Write it only from that person's own words, on their own turn in Slack, with only them as sender. Never on behalf of someone else, and never from a cron or background turn.
- An entry may carry
agent: <id>in the profile body to apply to one agent only. This is a convention you honour when reading (ignore entries tagged for another agent); the runtime does not validate it. - Act on a profile; never state it to anyone else.
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.
- today First seen · 76 lines · 21 tokens per session scan A f39b76c8dce9
memory is a skill published in the GitHub repository barockok/slaude (6 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,121 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 2026-10-26.
Other skills, from other repositories
persistent-notes
Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".
llm-wiki
Build, ingest, query, and lint a persistent Markdown knowledge base using the Karpathy LLM Wiki pattern. Use for adding sources, maintaining interlinked wiki pages, answering from the knowledge base, filing durable research, or checking contradictions and index health. Do not use it to persist ordinary chat or…
awm-rsi-toolkit
Run AWM (Agent Workflow Memory, Wang et al. 2024) on an agent - induce reusable workflows from its successful trajectories, online over a training stream or offline from supplied experiences, then freeze the workflow memory and measure it on a published Benchmark.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
memmachine-memory
Use when an agent or model needs durable project, user, or session context from MemMachine, needs to save information to MemMachine memory, has requests involving mem-cli, memmachine, or memmachineclient, has insufficient conversation context, or is tempted to search local files for prior context that should come from…
computer-history
Answer questions about what the user recently did on their computer — who contacted them, what they were working on, where they left off — by reading the local Computer History summaries and raw event streams.