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/soulcodex/agentic/deploy-confignpx skills add soulcodex/agentic --skill deploy-configgit clone --depth 1 https://github.com/soulcodex/agenticWhat 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 | $0.00064 | $0.00582 |
| Opus 5 | $0.00032 | $0.00291 |
| Sonnet 5 | $0.00013 | $0.00116 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
deploy-config 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
Deploy Config Skill
Deploy the complete agentic configuration to a target project.
Step 1 — Confirm Target and Profile
Ask the user:
- Target project path (absolute or relative)
- Profile name (run
just list-profilesif unsure) - Skills to deploy (run
just list-skillsif unsure; can be "all" or a comma-separated list) - Which vendors to generate files for
Step 2 — Check for Existing Config
Read {target}/.agentic/config.yaml if it exists.
If it does, show the current profile and version, and ask if the user wants to update or replace.
Step 3 — Run the Full Deploy Pipeline
# 1. Compose AGENTS.md from the profile
just compose {profile} {target}
# 2. Generate vendor-specific files
just vendor-gen {target} --vendors {vendors}
# 3. Deploy selected skills
just deploy-skills {target} --skills {skills}
Step 4 — Verify Output
After deploying, list the files created in the target project:
AGENTS.md— primary agent instructionsCLAUDE.md— Claude adapter (if claude vendor enabled).github/copilot-instructions.md— Copilot adapter (if copilot enabled)GEMINI.md— Gemini primary context file (auto-discovered, if gemini enabled).gemini/system.md— Gemini system-prompt override (requiresGEMINI_SYSTEM_MD=1, if gemini enabled).gemini/skills/— Gemini skills directory (symlinked, if gemini enabled).claude/skills/*/— deployed skill directories (if claude enabled).agentic/config.yaml— lock file recording what was deployed
Step 5 — Next Steps
Suggest to the user:
- Commit the generated files to the target project
- Run
just validate {target}to verify the config is valid - Run
just sync-check {target}periodically to detect drift from the library
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 · 69 lines · 64 tokens per session scan A 1856f4f0f469
deploy-config is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 582 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
pinme-uniwebpay
Use when generating, modifying, or reviewing PinMe Worker (Cloudflare Worker TypeScript) code that accepts payments through UniwebPay — payment links, products/prices, checkout sessions, payment status reads, refunds, subscriptions, or handling UniwebPay webhooks with @uniwebpay/sdk in a PinMe project.
pinme-r2
Use when a PinMe Cloudflare Worker needs R2 object storage, including secure file or image upload, streaming download, metadata lookup, deletion, listing, Range requests, or R2+D1 coordination. Guides AI to use PinMe's automatically injected env.R2 binding without R2 credentials or manual Wrangler configuration.
pinme-auth
Use when a PinMe project (Worker TypeScript) needs to integrate user authentication — creating email/password users, verifying idtokens, querying user info, or listing users via Identity Platform auth proxy APIs.
pinme-llm
Use this skill when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat/completions, streaming, or OpenRouter web search. Guides AI to generate correct Worker TS code.
survey-design
Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use a-b-test-design (prototyping-testing).
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).