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/tinyagi/tinyagi/skills-managernpx skills add TinyAGI/tinyagi --skill skills-managergit clone --depth 1 https://github.com/TinyAGI/tinyagiWhat 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 | $0.00094 | $0.00493 |
| Opus 5 | $0.00047 | $0.00246 |
| Sonnet 5 | $0.00019 | $0.00099 |
| Haiku 4.5 | $0.00009 | $0.00049 |
Grade A, and why
skills-manager 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 2d 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
Skills Manager
Search the skills registry and install skills to agent workspaces.
Available operations
Search skills
Search the registry for skills matching a query:
bash .agents/skills/skills-manager/scripts/skills-manager.sh search <query> [agent_id]
query— keyword to search for (e.g. "seo", "pdf", "browser")agent_id— optional; agent whose workspace to run the search from (defaults to current agent via settings)
Install a skill
Install a skill from the registry to an agent's workspace:
bash .agents/skills/skills-manager/scripts/skills-manager.sh install <skill_ref> <agent_id>
skill_ref— skill reference from search results (e.g. "@anthropic/seo" or a GitHub URL)agent_id— the agent to install the skill to
List installed skills
List skills currently installed in an agent's workspace:
bash .agents/skills/skills-manager/scripts/skills-manager.sh list [agent_id]
If agent_id is omitted, lists skills for all agents.
Workflow
- Search the registry to find a skill:
skills-manager.sh search "image editing" - Review the results — note the skill reference string
- Install it to the target agent:
skills-manager.sh install <ref> <agent_id> - Verify with list:
skills-manager.sh list <agent_id>
Notes
- The TinyAGI API must be running (
tinyagi start) for search and install via API - Search uses the
skillsCLI under the hood (auto-installed via npx) - Install places skills into the agent's
.agents/skills/directory - Installed skills are automatically available to the agent on its next invocation
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 57 lines · 94 tokens per session scan A 4752d9a3a794
skills-manager is a skill published in the GitHub repository TinyAGI/tinyagi (3,611 stars, last pushed 5mo ago), licensed MIT. It adds 94 tokens to every session and 493 once invoked, about $0.0005 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
paperclip
Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.
omni-mcp
Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.
add-resend
Add Resend (email) channel integration via Chat SDK.
codegen
Code generation utilities for json-render. Use when generating code from UI specs, building custom code exporters, traversing specs, or serializing props for @json-render/codegen.
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
optimize-agentic-workflow
Analyze and reduce token consumption in agentic workflows — guardrail-specific entry points, measurement, and optimization techniques.