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 skills/gideondk/strata/forgetnpx skills add gideondk/strata --skill forgetgit clone --depth 1 https://github.com/gideondk/strataWrote 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/gideondk/strata/forget)<a href="https://agentmods.dev/skills/gideondk/strata/forget"><img src="https://agentmods.dev/badge/skills/gideondk/strata/forget.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.00754 |
| Opus 5 | $0.00056 | $0.00377 |
| Sonnet 5 | $0.00022 | $0.00151 |
| Haiku 4.5 | $0.00011 | $0.00075 |
Grade A, and why
strata:forget scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
strata:forget
Moving > deleting. Files go to <vault>/<repo>/.trash/ with a timestamped
Filename and a JSONL audit-log entry. The vault search stops returning them;
they're still on disk if you need them back.
When to use
- A note holds PHI/secrets that can't safely be scrubbed in place.
- GDPR / right-to-erasure request from a data subject.
- A domain note was wrong and you don't want it showing up in search.
- Cleanup after a hasty
/strata:save.
How
Two-step with --dry-run for safety.
# 1. Preview
"${CLAUDE_PLUGIN_ROOT}/bin/strata" forget \
--path decisions/2026-05-20-mistake.md \
--reason "Erasure request — ticket #1234" \
--dry-run
# 2. Apply
"${CLAUDE_PLUGIN_ROOT}/bin/strata" forget \
--path decisions/2026-05-20-mistake.md \
--reason "Erasure request — ticket #1234"
--reason is required and is recorded in the audit log. Be specific —
"cleanup" is fine for trivial cases, but for regulatory erasure include the
Ticket / request reference.
Audit log
Each forget writes a line to <vault>/<repo>/.audit.log:
{"ts":"2026-05-21T13:42:11Z","action":"forget","src":"decisions/...","dest":".trash/2026-05-21-1342--decisions__...","size":1842,"sha256":"abc…","by":"<git user.name>","reason":"<your reason>"}
Fields: ISO-8601 timestamp, action, source path, trash path, byte size, sHA-256 of the file contents at forget time, author, reason.
The log is append-only (no script deletes from it). If you sync the Vault via git, commit the log to give the deletion a blameable history.
Recovery
Just move the file back:
mv ~/StrataVault/myrepo/.trash/2026-05-21-1342--decisions__... \
~/StrataVault/myrepo/decisions/2026-05-20-mistake.md
(The flattened filename in trash uses __ for / so it's recoverable
Unambiguously.)
What it doesn't do
- Doesn't redact other notes that wikilink to the forgotten one — those
become unresolved links, which
/strata:reviewwill surface. - Doesn't propagate the deletion to other team members' vaults — sync mechanism handles that.
- Doesn't
shredthe file. If your threat model requires actual deletion (not "moved to trash"), follow up withrmand agit filter-branchif applicable.
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.
- 3d ago First seen · 76 lines · 111 tokens per session scan A d83b8cb5f5f9
strata:forget is a skill published in the GitHub repository gideondk/strata (5 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 111 tokens to every session and 754 once invoked, about $0.0006 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 skills, from other repositories
my-wiki
Manage local OKF-compatible Markdown My Wiki vaults with an AI agent. Use for capturing webpages, PDFs, Office documents, notes, images, folders, and ZIP bundles as References; maintaining Reference-to-Concept evidence links; searching or answering from a vault; checking or repairing vault health; switching among…
kb
Operate a hraness/kb local-first Markdown knowledge base for coding-agent memory. Use when a user asks to search or query a KB or Obsidian vault; load repository context, plans, decisions, concepts, backlinks, semantic search, or Git provenance; save, clip, scrape, or archive a URL, article, social thread, signed-in…
memory-forest
Build, validate, index, and query a private local Memory Forest with provenance-aware layers, pointer-first search, and validated root-first retrieval. Use when creating a new forest, checking an existing forest's structure, building its local SQLite index, or retrieving bounded memory trails without exposing full…
memory-forest-retrieve
Integrate a mandatory, metadata-only Memory Forest consultation gate before an agent responds to each non-empty user-authored text turn.
brain
Orient in the user's big-brain second brain and work brain-aware for the rest of the session. Use when the user types /brain, or asks "what am I working on", "what's on my plate", "catch me up", "what's overdue", or at the start of a session about ongoing work. Loads the vault overview, reports it in one screen, and…
capture
Quick-capture a thought, idea, link, or fact into the big-brain second brain's inbox. Use when the user types /capture , or says "note this down", "remember this in my brain", "add to my inbox", "capture this idea". Zero-friction: file it now, organize later.