Borrowing it
Nothing to install: this file belongs to jazzyalex/agent-sessions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jazzyalex/agent-sessions/main/.agents/skills/deploy-agent-sessions/SKILL.mdgit clone --depth 1 https://github.com/jazzyalex/agent-sessionsWrote 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/jazzyalex/agent-sessions/deploy-agent-sessions)<a href="https://agentmods.dev/skills/jazzyalex/agent-sessions/deploy-agent-sessions"><img src="https://agentmods.dev/badge/skills/jazzyalex/agent-sessions/deploy-agent-sessions/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/jazzyalex/agent-sessions/deploy-agent-sessions"><img src="https://agentmods.dev/badge/skills/jazzyalex/agent-sessions/deploy-agent-sessions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00075 | $0.00762 |
| Opus 5.5 | $0.00030 | $0.00305 |
| Sonnet 5.5 | $0.00015 | $0.00152 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
deploy-agent-sessions 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 1mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Sessions Deploy
Canonical sources
When working in the Agent Sessions repo, treat these as the single source of truth:
.claude/skills/deploy.mddocs/deployment.md- Unified tool:
tools/release/deploy(start withtools/release/deploy --help)
If this skill conflicts with any of the above, follow the repo docs.
Workspace policy (mandatory)
- Always deploy from the user’s current local repository checkout.
- Do not create temporary clones or alternate worktrees to work around a dirty tree.
- If the local worktree is dirty, stop and advise the user to clean it first (commit, stash, or discard), then continue in the same local repo.
Default workflow (command sequence)
Use the unified deploy tool, following .claude/skills/deploy.md:
tools/release/deploy changelog [FROM_TAG]
tools/release/deploy qa --version <VERSION>
tools/release/deploy bump [patch|minor|major]
git push origin main
tools/release/deploy qa --version <VERSION>
tools/release/deploy release <VERSION> [--dry-run]
tools/release/deploy verify <VERSION>
Before running release
- Confirm target version string (
X.Yfor major/minor releases,X.Y.Zonly for patch releases) and whether this is a patch/minor/major bump. Never shipX.Y.0. - Ensure user-visible notes are updated (per
.claude/skills/deploy.md):docs/CHANGELOG.md, monthly summary indocs/summaries/YYYY-MM.md, and any required public copy updates. - Run
tools/release/deploy qa --version <VERSION>on the exact release commit. QA requires a cleanmaincheckout synced withorigin/main;tools/release/deploy releaseandtools/release/deploy resumerequire its fresh QA stamp unless--skip-qa/SKIP_QA=1is explicit. - The QA gate is CI-parity: it verifies the pinned Xcode toolchain, runs the docs guards and localization catalog validation, runs a no-signing Debug build in
.deriveddata-localization, and runs localization extraction-drift validation before writing the QA stamp. A green XCTest run alone is not release-ready. - If user-facing SwiftUI copy changed, update
AgentSessions/Resources/Localizable.xcstringsin the same change. Keep intentional raw paths, commands, and identifiers asText(verbatim:); add validator verbatim exceptions only after review. tools/release/deploy bumprequires the target-version QA stamp before changing release metadata; after pushing the bump commit, rerun exact-commit QA before release. Never use the manual fallback to bypass a failed QA/extraction gate.- Local QA must match
tools/release/ci-xcode-version.txt; CI selects that toolchain on the pinnedmacos-26image. - Expect Release builds to spend several minutes in
swift-frontendduring whole-module optimization; the build helper now prints heartbeats. If interrupted after the notarized DMG is built, prefertools/release/deploy resume, which validates the saved gitHEADbefore continuing.
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.
- 1mo ago First seen · 48 lines · 75 tokens per session scan A 73338a618850
deploy-agent-sessions is a skill published in the GitHub repository jazzyalex/agent-sessions (918 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 762 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-22.
Other skills, from other repositories
pdlc-ship
A software release workflow that runs tests, updates the version and change log, creates a Git tag, and starts CI/CD, the automated build and deployment process.
tfx-ship
A release workflow for publishing triflux versions through GitHub Releases, the npm package registry, and the Claude Code marketplace. It also supports version changes, dry runs, skipped tests, and no-publish runs.
automating-devops
DevOps knowledge reference covering Git workflows, testing strategies, DevSecOps, release pipeline orchestration (release.yml, multi-arch images, cosign integration), CI/CD pipelines, database management, observability, and performance optimization. Use when working with Git, CI/CD, release pipelines, ghcr image…
codexkit-repository-maintenance
Use when maintaining or improving the GameStudio-CodexKIT source repository, including CI, governance, catalog, generators, adapters, packaging, documentation, versioning, or release readiness.
tendril-release
Updates the used Ivy NuGet packages to the latest stable versions in a branch from development, builds/verifies, merges into development, creates a PR into main, merges it, merges main back to development, and triggers the GitHub Actions release workflow.
release-candidate-preflight
Use when a release candidate or RC needs a go/no-go readiness decision across required artifacts, test summaries, known issues, approvals, compatibility, monitoring, and rollback.