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 staticgit 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/static)<a href="https://agentmods.dev/skills/fergana-labs/stash/static"><img src="https://agentmods.dev/badge/skills/fergana-labs/stash/static/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/fergana-labs/stash/static"><img src="https://agentmods.dev/badge/skills/fergana-labs/stash/static.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 228 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 5 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 69 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00000 | $0.02302 |
| Opus 5.5 | $0.00000 | $0.00921 |
| Sonnet 5.5 | $0.00000 | $0.00460 |
| Haiku 4.5 | $0.00000 | $0.00230 |
Grade A, and why
static scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST {{BASE_URL}}/api/v1/users/register \ How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stash — Files, Skills, and Memory System
Concept: Your Stash and Skills
Stash is your personal home for agent work. Everything you create is scoped to your account — it is yours alone, with nothing to pick or set up first. Your Stash has three primary surfaces:
- Sessions — agent transcripts uploaded under
/api/v1/me/sessions. - Files — folders, markdown pages, HTML pages, uploads, and tables.
- Skills — modules of agent-usable knowledge: local SKILL.md folders and shareable bundles of sessions and Files.
To give your agents a skill, create a Files folder whose immediate children
include a file named SKILL.md. The body of SKILL.md starts with YAML
frontmatter:
---
name: dd-respond
description: Draft response packets to investor diligence asks
when_to_use: When an investor sends a DD checklist
version: 2.1
mcp_exposed: true
---
The folder may contain any number of supporting .md files (examples.md,
checklist.md, etc.) — they all become part of the skill payload. Stash
exposes skills via:
GET /api/v1/me/skills— list your skillsGET /api/v1/me/skills/{name}— full skill (SKILL.md + siblings)- MCP:
stash_list_skills,stash_read_skill
This is the same skills convention Claude Code uses, so a skill authored in
Stash works directly when dropped into any agent's ~/.claude/skills/ folder.
Overview
Stash is the product surface for you and your agents.
It provides:
- pages organized in nestable folders
- tables (typed columns, rows, CSV import/export, semantic row search)
- session events (with file attachments)
- file uploads (S3-backed; PDF/image text extraction when available)
- Skills for publishing sets of pages, sessions, and files
Design boundary:
- Stash owns persistent state and plugin-based memory access
- external orchestration layers own multi-agent delegation
- Claude-session memory access should go through the Stash plugin, not side-channel polling
Base URL
{{PUBLIC_URL}}
Authentication
All endpoints (except registration and a few public lookups) require an API key:
Authorization: Bearer st_xxxxxxxxxxxxx
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 First seen · 245 lines · 0 tokens per session scan A 71ac199d1786
static is a skill published in the GitHub repository Fergana-Labs/stash (337 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,302 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
antigravity-cli
Use Antigravity CLI as a subagent. Lets the main agent prompt Antigravity CLI from the terminal in headless mode with the agy command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Antigravity CLI, when a task needs a second independent agent, or when a plan…
slash-command-skill-classification-filter
Derive a slash-command skill surface from a broader prompt-command registry by requiring descriptive metadata, excluding builtins, and admitting only a controlled set of origins plus explicit user-only commands.
memoized-command-source-aggregation
Load independent command sources in parallel, then memoize the merged registry by cwd so repeated lookups stay cheap and ordered.
skip-skill-discovery-on-skill-expansion
Bypass skill discovery when expanded SKILL.md or generated prompt content is being reprocessed for attachments, so non-user text does not trigger recursive discovery work.
turn-zero-vs-inter-turn-skill-discovery-split
Block skill discovery only on the initial user message; run later discovery asynchronously while tools execute using the write-pivot guard.
lazy-heavy-command-shims
Stub heavy commands so the CLI stays light, loading the real implementation only when the command is executed.