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/veryfront/veryfront-code/deploy-safelynpx skills add veryfront/veryfront-code --skill deploy-safelygit clone --depth 1 https://github.com/veryfront/veryfront-codeWhat 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 | $0.00022 | $0.00433 |
| Opus 5 | $0.00011 | $0.00217 |
| Sonnet 5 | $0.00004 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
deploy-safely 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 Safely
Build and test the reviewed Git source, then push it to Veryfront before creating a release and deployment. If verification fails, revert the Git commit and run the normal delivery sequence again.
Steps
-
Build
veryfront build --jsonAbort if
success: false. -
Run tests
veryfront test --jsonAbort if any test fails.
-
Push
veryfront push --branch <branch> --yesAbort if any file fails to upload.
-
Deploy
veryfront deploy --env <environment> --branch <branch> --yes --jsonRecord the project, environment, release, deployment, and commit IDs from the final result record.
-
Verify health (via MCP) Use
vf_get_errorsto check for runtime errors after deploy. Wait 30 seconds, then check again. -
Confirm or rollback
- If no errors: deployment is successful
- If errors are detected, create and push a Git revert:
git revert <bad-commit> git push origin <branch> - Let CI run the normal Push and Deploy steps for the revert. Without CI, repeat steps 3 and 4 manually.
Error Recovery
- Build fails: Check
vf_get_errorsfor compilation errors, fix and retry - Tests fail: Read the JSON output and fix failing tests
- Push fails: Fix the upload failure and rerun Push before Deploy
- Deploy fails: Check environment name, auth token, branch existence
- Post-deploy errors: Revert the failing Git commit, push the revert, then run the normal Push and Deploy sequence
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 · 58 lines · 22 tokens per session scan A 3b730c17a402
deploy-safely is a skill published in the GitHub repository veryfront/veryfront-code (18 stars, last pushed 2d ago), licensed Apache-2.0. It adds 22 tokens to every session and 433 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
rove
Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.
general-video
The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a…
motion-graphics
Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s…
release
Autonomously cut a Rove (@sma1lboy/rove) release end-to-end — detect the semver bump from pending changesets (flagging an upstream minor you didn't intend), run the release gates, bump/tag/push via scripts/release.sh, then poll the GitHub Actions Release workflow with gh until npm publish completes, diagnosing CI…
file-issue
Turn a rough idea, a bug, or a batch of unsolved problems into well-structured GitHub issue(s) and file them with gh, auto-classifying type + labels from the content (recommend, then confirm) and following Rove's conventions (beginner-friendly framing, concrete file pointers, an acceptance checklist, zero AI/Anthropic…
hyperframes-cli
HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, or remove-background, or when troubleshooting the…