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/netgrade-digital/shared-agents/sa-clinpx skills add netgrade-digital/shared-agents --skill sa-cligit clone --depth 1 https://github.com/netgrade-digital/shared-agentsWhat 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 | $0.00069 | $0.03506 |
| Opus 5 | $0.00034 | $0.01753 |
| Sonnet 5 | $0.00014 | $0.00701 |
| Haiku 4.5 | $0.00007 | $0.00351 |
Grade E, and why
sa-cli scanned grade E with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/netgrade-digital/shared-agents/refs/heads/main/scripts/bootstrap.sh | bash Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| Wizard cancelled, half setup | `rm -rf ~/.shared-agents` · `sa bootstrap` again | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/netgrade-digital/shared-agents/refs/heads/main/scripts/bootstrap.sh | bash How it starts
The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shared-agents CLI (sa)
Canonical live help: run sa or sa help — prefer that over memorizing flags.
sa # help overview (default)
sa help # same
shared-agents … # alias
sharedagents … # alias
Without shell aliases (agents, CI, fresh shell):
"${SHARED_AGENTS_HOME:-$HOME/.shared-agents}/scripts/sa" help
Repo root (dev checkout): ./sa · ./sa install
Env: SHARED_AGENTS_HOME (default ~/.shared-agents) · Version: sa version
First-time setup
Recommended (Core + private team repo + adapters):
curl -fsSL https://raw.githubusercontent.com/netgrade-digital/shared-agents/refs/heads/main/scripts/bootstrap.sh | bash
# Piped curl uses /dev/tty for the wizard when possible (TUI or text prompts).
# Force auto-install only: SA_BOOTSTRAP_NON_INTERACTIVE=1 curl … | bash
# or after clone: ./scripts/bootstrap.sh · sa bootstrap
source ~/.bashrc
sa check
sa team verify # optional but useful after bootstrap
Classic (Core only, then wizard — team repo optional in wizard):
git clone [email protected]:netgrade/shared-agents.git ~/.shared-agents
cd ~/.shared-agents
./sa install
source ~/.bashrc
From dev checkout without ~/.shared-agents yet: ./sa install — wizard runs before clone; cancel leaves no ~/.shared-agents.
New AI tool installed? → run sa install again.
Commands (overview)
| Area | Command | Summary |
|---|---|---|
| Info | sa · sa help |
All commands |
| Info | sa version |
CLI version + HOME |
| Setup | sa bootstrap |
Full first-time setup (Core + team + adapters) |
| Setup | sa install |
Setup wizard (default in TTY) |
| Setup | sa install --non-interactive |
All detected tools, no prompts |
| Setup | sa install --wizard |
Wizard explicitly |
| Setup | sa check |
Tool installed vs configured (+ team warnings) |
| Setup | sa sync |
Pull Core + team; link skills + rules |
| Setup | sa status |
Open items: review, skills, adapters, team |
| Setup | sa doctor |
Diagnose symlink / rule link issues |
| Setup | sa doctor --fix |
Repair (backup + relink blocking rule files) |
| Setup | sa team verify |
Deep team repo validation |
| Setup | sa team migrate |
Legacy learnings/ → team/learnings/ |
| Setup | sa uninstall |
Uninstall (y/N) |
| Learnings | sa review |
Interactive: pending → approved |
| Learnings | sa review list |
Pending list |
| Learnings | sa review dry [file] |
Dry-run |
| Learnings | sa pending push [file] |
Commit + push pending |
| Learnings | sa pending path [slug] |
Canonical pending path |
| Learnings | sa unapprove [id|file] |
Remove from approved |
| Learnings | sa unapprove list |
Approved list |
| Team content | sa skill new |
Wizard: team/skills/<name>/SKILL.md |
| Team content | sa skill rm [name] |
Remove team skill |
| Team content | sa skill list |
List team skills |
| Team content | sa skill edit [name] |
Edit team skill (opens $EDITOR) |
| Team content | sa rule new |
Wizard: team/rules/<slug>.mdc |
| Team content | sa rule rm [slug] |
Remove team rule |
| Team content | sa rule list |
List team rules |
| Team content | sa rule edit [slug] |
Edit team rule (opens $EDITOR) |
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.
- yesterday First seen · 389 lines · 69 tokens per session scan E a50327d8b98e
sa-cli is a skill published in the GitHub repository netgrade-digital/shared-agents (4 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 3,506 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
auth-web-cloudbase
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.
fix-codesign-error
Slash command that inspects a macOS signing or entitlement failure and explains the minimum fix path. Invoke explicitly with /fix-codesign-error — this skill never self-triggers.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.