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/sachinshelke/codevira/release-readinessnpx skills add sachinshelke/codevira --skill release-readinessgit clone --depth 1 https://github.com/sachinshelke/codeviraWrote 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/sachinshelke/codevira/release-readiness)<a href="https://agentmods.dev/skills/sachinshelke/codevira/release-readiness"><img src="https://agentmods.dev/badge/skills/sachinshelke/codevira/release-readiness.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00096 | $0.01774 |
| Opus 5 | $0.00048 | $0.00887 |
| Sonnet 5 | $0.00019 | $0.00355 |
| Haiku 4.5 | $0.00010 | $0.00177 |
Grade A, and why
release-readiness 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release readiness — the bypass-proof release gauntlet
v2.0.0 shipped to PyPI with 23 silent-failure bugs because nothing forced gauntlet-pass evidence before publish. This skill makes the gauntlet mandatory at the CONVERSATION layer (skills); the Makefile
- hook + CI enforce it at the TOOL layer. Both must agree before any release proceeds.
When this skill triggers
Trigger phrases:
- "ready to release"
- "let's ship"
- "publish to PyPI"
- "promote to production"
- "release X.Y.Z"
- "cut a release"
- "tag the version"
- "ship it"
- Any mention of
twine upload,gh release create --draft=false,pipx publish, etc.
When this skill triggers, you MUST walk the 5-gate gauntlet below before producing any actual release command.
The 5 gates
Defined in codevira.discipline.yaml::release_gates. Each must pass.
G1 — Unit tests
make test-unit
# OR: pytest tests/ -q --ignore=tests/e2e
Pass criterion: exit code 0, no test failures or unexpected skips.
G2 — First-contact e2e
make test-e2e
# OR: pytest tests/e2e/test_first_contact.py -v
Pass criterion: all 4 fixtures pass (docs_only, code_only_python, polyglot, monorepo). This is the gate that catches bugs A–O. If G2 shows failures, those failures ARE the v2.1 work list — don't release until they're fixed.
G3 — Real-IDE smoke
scripts/check_real_ide_smoke.sh
Pass criterion: codevira appears connected in Claude Code AND Claude
Desktop AND at least one other IDE. tools/list returns in <1s.
Today's state: the script is a stub. Until it's filled in, G3 = "skipped" in evidence. That's tolerable for v2.0.x releases but BLOCKING for v2.1's launch.
G4 — Crash-log clean
test "$(codevira report 2>/dev/null | grep -c CRASH)" = "0"
Pass criterion: zero CRASH entries in ~/.codevira/logs/crashes.log
after the e2e gauntlet has run. Catches the Chroma HNSW writer
corruption pattern that UDAP hit with 41 crashes from one session.
G5 — Human-in-the-loop
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.
- 5d ago First seen · 210 lines · 96 tokens per session scan A 84296714de63
release-readiness is a skill published in the GitHub repository sachinshelke/codevira (12 stars, last pushed 20d ago), licensed MIT. It adds 96 tokens to every session and 1,774 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
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
ci-cd-pipelines
When designing GitHub Actions workflows, optimizing pipeline speed, implementing deployment gates.
shipping-and-launch
Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
shipping-and-launch
准备生产发布。用于准备部署到生产环境时；用于需要发布前检查清单、设置监控、规划分阶段发布，或需要回滚策略时。.
production-deployment
Zero-downtime deployments with pre-flight checks, staged rollouts, and rollback plans. Never ship to production without a verified rollback strategy.
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…