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/fergana-labs/stash/overviewnpx skills add Fergana-Labs/stash --skill overviewgit 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/overview)<a href="https://agentmods.dev/skills/fergana-labs/stash/overview"><img src="https://agentmods.dev/badge/skills/fergana-labs/stash/overview.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 5.1 | $0.00023 | $0.00540 |
| Opus 5 | $0.00012 | $0.00270 |
| Sonnet 5 | $0.00005 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
overview 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 6d 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
Overview of a saved library
A chart on its own is decoration. Every chart here answers a question the user would otherwise have to ask, and you say the answer in words next to it.
Get the data
From the Bookmarks table via query_table. You need the whole table, not
a page — read total from the first call and page with offset until you
have it. Counting 100 of 4,000 saves and calling it a distribution is worse
than not charting at all.
Columns you'll use: Saved (ISO date), Topics (array), Site, Type,
Status.
The four that earn their place
- Saves over time — by week or month. Answers "am I still using this?" and shows bursts, which usually map to a project.
- Topics by volume — horizontal bars, biggest first. Answers "what am I actually collecting?" Cap at the top 12 and group the tail as "other"; a bar chart with 60 labels communicates nothing.
- Sources — top domains. Answers "where does my reading come from?" Often uncomfortable and therefore useful.
- Topic over time — the top few topics as lines. Answers "what am I moving toward, and what have I dropped?"
Skip any chart the data can't support. Fewer than ~20 saves, or fewer than three distinct topics, means the honest output is a sentence, not a chart.
Say what it means
Under each chart, one or two sentences of what it shows — the actual reading, not a caption. "Two thirds of your saves are from three domains" is worth writing. "This chart shows saves by domain" is not.
Close with what stands out across all four: a topic that stopped, a source that dominates, a burst that maps to something they were building.
Rules
- Charts follow the repo's dataviz conventions. Render as an HTML page in the user's stash so they can keep it.
- Label axes and units. Never a pie chart with more than five slices.
- Say the corpus size and date range you charted, so the reader knows what they're looking at.
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.
- 6d ago First seen · 54 lines · 23 tokens per session scan A e1a50fec590c
overview is a skill published in the GitHub repository Fergana-Labs/stash (332 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 540 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
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
gsd-ns-manage
Route to the appropriate management skill based on the user's intent. gsd-config (settings + advanced + integrations + profile) and gsd-workspace (new + list + remove) are post-#2790 consolidated entries.