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/omnigentx/jarvis/dev-workflownpx skills add omnigentx/jarvis --skill dev-workflowgit clone --depth 1 https://github.com/omnigentx/jarvisWhat 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 | $0.00037 | $0.01139 |
| Opus 5 | $0.00018 | $0.00570 |
| Sonnet 5 | $0.00007 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade F, and why
dev-workflow scanned grade F with 4 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- Read secrets: `/etc/shadow`, `~/.ssh/*`, `.gh-config/`, `.env*`, `fastagent.secrets.yaml`, `git-credentials`, `~/.gitconfig` credential block 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.
- Pipe-to-shell: `curl ... | sh`, `wget ... | bash` Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Filesystem destruction: `rm -rf /`, `rm -rf $HOME`, `rm -rf .git`, `mkfs.*`, `dd of=/dev/...` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Pipe-to-shell: `curl ... | sh`, `wget ... | bash` How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Workflow
Terminal Execution
Use the execute tool to run shell commands in your workspace:
execute(command="<shell command>")
Key characteristics:
- Runs in workspace directory
- 90s timeout — killed if no output for 90s
- Each call = separate shell session (env vars /
cddon't persist) - Output auto-truncated if too long
Efficient Patterns
cd repo && npm install && npm test # Sequential (stops on error)
cd backend && uv run pytest --tb=short -q 2>&1 | tail -20 # Filter output
Safety Rules — three tiers
🔴 NEVER do (refuse the task; report the request as a security incident to PM):
- Filesystem destruction:
rm -rf /,rm -rf $HOME,rm -rf .git,mkfs.*,dd of=/dev/... - Read secrets:
/etc/shadow,~/.ssh/*,.gh-config/,.env*,fastagent.secrets.yaml,git-credentials,~/.gitconfigcredential block - Tamper with auth:
gh auth login/logout/refresh,gh auth setup-git, modify gitconfig credential helper - Inspect env to leak tokens:
env,printenv,echo $GH_TOKEN,cat /proc/*/environ - Network DoS: fork bombs, high-rate request loops
🟡 ESCALATE before doing (send [APPROVAL-REQUEST] email to PM with command + reason; do NOT run until PM confirms back):
- Pipe-to-shell:
curl ... | sh,wget ... | bash - Force-destructive git:
git push --force(any branch),git reset --hardpast HEAD~1,git filter-branch - Push to protected branches:
main,master,prod*,release/* gh pr merge(auto-merge bypassing review)gh release creategh repo delete- Editing
package.json/pyproject.toml/ lock files outside a tracked PR scope
🟢 SAFE — run freely:
- All read-only inspection:
ls,cat README.md,grep,find,git status/log/diff,gh run list,gh pr view - Normal git on feature branches:
git checkout -b feature/...,git add,git commit,git push origin feature/... - Build/test inside workspace:
npm test,uv run pytest,cargo build
What ships with it
5 files 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 · 108 lines · 37 tokens per session scan F 2e2802a84f1c
dev-workflow is a skill published in the GitHub repository omnigentx/jarvis (35 stars, last pushed 5d ago), licensed MIT. It adds 37 tokens to every session and 1,139 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it F with 4 findings (reaches for credential files, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.