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 Fergana-Labs/stash --skill briefgit clone --depth 1 https://github.com/Fergana-Labs/stashWrote 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/fergana-labs/stash/brief)<a href="https://agentmods.dev/skills/fergana-labs/stash/brief"><img src="https://agentmods.dev/badge/skills/fergana-labs/stash/brief.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00528 |
| Opus 5 | $0.00012 | $0.00264 |
| Sonnet 5 | $0.00005 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
brief 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 8d 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.
What it actually says
Briefing new saves
A period's saves are not a list to recite. The user already knows they saved things; what they don't know is what those saves add up to. Lead with the thread, not the inventory.
Get the set
Saves live in the Bookmarks table. Use query_table with a date filter
on the Saved column — dates are ISO strings, so gte compares correctly:
query_table(table_name="Bookmarks",
filters=[{"column_id": "<Saved>", "op": "gte", "value": "2026-07-20"}],
limit=100)
query_table returns the column list, so read the ids off that rather than
guessing. It also returns total — if it exceeds your limit, page with
offset before writing anything. Never brief on a partial set without saying
so.
Each row carries a Summary and Topics already, written when the item was
saved. Use them. Only open the full saved copy (the Clip link) when the
summary is too thin to place the item.
Write it
- The thread — two or three sentences on what connects this period's saves. If nothing connects them, say that; a week of scattered saves is a real finding, not a failure to look hard enough.
- What's worth your time — at most three items, each with why this one and a link. Rank by what the user seems to be working on, not by what's most impressive.
- The rest — one line each, grouped by topic, linked.
- Untouched — anything saved in the period they haven't opened since. Say it plainly; don't nag.
Rules
- Every claim links to the item it came from.
- No outside knowledge. If context helps, mark it "(context, not from your saves)".
- If the period is empty, say so in one line and stop. Do not pad.
- Write it as a page in the user's stash next to the material, when you can write pages; otherwise put it in the chat.
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.
- 8d ago First seen · 54 lines · 23 tokens per session scan A 9aecdf31d610
brief is a skill published in the GitHub repository Fergana-Labs/stash (332 stars, last pushed 5d ago), licensed MIT. It adds 23 tokens to every session and 528 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 2026-08-30.
Other skills, from other repositories
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
loadout-remember
Save a durable, cross-project user preference into loadout's global fragments/profiles — or update the fragment it contradicts. Use when the user states lasting guidance that should follow them across projects and agents ("always X", "never Y", "stop doing Z"), especially when it conflicts with guidance the loadout…
atomicmemory
Persistent semantic memory across Claude Code sessions — user preferences, project context, prior decisions, codebase facts. Call memorysearch before answering questions that reference past work. Call memoryingest after the user shares durable facts.
atomicmemory-cli
Use the installed AtomicMemory CLI for memory search, ingestion, packaging, diagnostics, and agent-safe JSON output.
agent-context
Create, validate, and maintain a structured .agent-context directory for a repository so AI agents navigate the codebase efficiently and make higher-quality decisions. Use when setting up agent context for a new repo, updating context after agent work, or catching up context after human work.
first-tree-sync
Audit and repair drift between merged code and the Context Tree in both directions — tree→code (does code still support tree facts?) and code→tree (does the tree register everything code now contains?). Use when the tree may be stale, wrong, outdated, or missing coverage for recent code changes; after a large merge…