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 skills add oborchers/fractional-cto --skill tag-based-production-deploysgit clone --depth 1 https://github.com/oborchers/fractional-ctoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/oborchers/fractional-cto/tag-based-production-deploys)<a href="https://agentmods.dev/skills/oborchers/fractional-cto/tag-based-production-deploys"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/tag-based-production-deploys/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/oborchers/fractional-cto/tag-based-production-deploys"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/tag-based-production-deploys.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 72 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 291 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 332 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Data Exfiltration · line 266 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 306 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What 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 5.1 | $0.00092 | $0.03300 |
| Opus 5 | $0.00046 | $0.01650 |
| Sonnet 5 | $0.00018 | $0.00660 |
| Haiku 4.5 | $0.00009 | $0.00330 |
Grade A, and why
tag-based-production-deploys scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
STATUS=$(curl -s -o /dev/null -w "%{http_code}" https://api.myapp.com/health) How it starts
The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Deploys on Push, Prod Deploys on Tag -- No Exceptions
There is a critical difference between "code was merged" and "we decided to release." Branch-based production deploys collapse this distinction. A merge to main is a code integration event -- it means the code passed review and tests. It does not mean someone decided the system is ready for production traffic. A git tag is a deliberate, auditable act. Someone looked at the state of main, decided it was ready, and explicitly said "this is a release." That intentionality is the difference between controlled releases and accidental deployments.
Development environments should deploy continuously from branch pushes -- fast feedback, low ceremony. Production environments deploy only from git tags -- explicit, deliberate, with approval gates. This separation provides an audit trail (tags are immutable references), intentionality (creating a tag is a conscious decision), rollback clarity (deploy the previous tag), and compliance evidence (every production change has a traceable trigger).
The Environment/Trigger Matrix
| Environment | Trigger | Branch/Tag | Approval Required | Purpose |
|---|---|---|---|---|
| Dev | Push to main |
Branch | None | Fast feedback, continuous integration |
| Production | Git tag creation | Semver (e.g., 1.2.3) |
Manual approval gate | Deliberate release with audit trail |
Why This Matrix Works
Dev deploys are cheap. A broken dev environment wastes 30 minutes. The team fixes it and moves on. Speed matters more than ceremony. Push to the branch, deploy automatically, see results immediately.
Production deploys are expensive. A broken production environment wastes revenue, trust, and sleep. Ceremony matters more than speed. The extra 60 seconds to create a tag and approve a gate is trivially cheap insurance against accidental deployments.
Tag Naming Convention
Use semantic versioning. The v prefix is optional -- both v1.2.3 and 1.2.3 work with every major CI/CD platform's tag-based triggers. Pick one convention and stick with it.
What ships with it
2 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.
- 11d ago First seen · 353 lines · 92 tokens per session scan A f521381981a5
tag-based-production-deploys is a skill published in the GitHub repository oborchers/fractional-cto (30 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 3,300 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. (gstack).
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
releasepr
Adopt, configure, run, or troubleshoot compozy/releasepr in a consuming repository, including Actions, beta/stable/legacy plans, notes, dry-runs, and publication. Excludes pr-release internals and general versioning advice.
gitlab-devops
GitLab DevOps operations — issues, merge requests, CI/CD pipelines, repository browsing, labels, milestones, releases, and wiki management. Use when querying GitLab project status, monitoring pipeline executions, browsing repository files, creating issues for network findings, opening merge requests for config…
seed-snapshot-release
An automated workflow for creating and tracking a snapshot release of the pull request on the current branch. A snapshot release is a temporary package build used for testing a branch before a normal release.