Agentic Context Engine is an open-source engine that gives AI agents a persistent learning loop, helping them remember successful strategies and learn from failures across sessions. It is used to improve production agents, and also powers Kayba’s hosted service. Catalogue add-ons support workflows for operating and configuring the engine.
Borrowing it
Nothing to install: this file belongs to kayba-ai/agentic-context-engine. 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/kayba-ai/agentic-context-engine/main/.claude/commands/release.mdgit clone --depth 1 https://github.com/kayba-ai/agentic-context-engineWrote 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/commands/kayba-ai/agentic-context-engine/release)<a href="https://agentmods.dev/commands/kayba-ai/agentic-context-engine/release"><img src="https://agentmods.dev/badge/commands/kayba-ai/agentic-context-engine/release/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/commands/kayba-ai/agentic-context-engine/release"><img src="https://agentmods.dev/badge/commands/kayba-ai/agentic-context-engine/release.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 | $0.00000 | $0.00971 |
| Opus 5.5 | $0.00000 | $0.00388 |
| Sonnet 5.5 | $0.00000 | $0.00194 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade A, and why
release 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 2mo 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
Release a new version: bump version, update changelog, tag, push, and create a GitHub release.
Arguments: $ARGUMENTS — the new version number (e.g. 0.9.0). Required.
Steps:
-
Validate inputs
- If $ARGUMENTS is empty, abort: "Usage: /release (e.g. /release 0.9.0)"
- Strip leading
vif present (e.g.v0.9.0→0.9.0) - Validate format matches
X.Y.Z(semver)
-
Validate branch state
- Must be on
main:git branch --show-current - If not on main, abort: "Switch to main first."
- Pull latest:
git pull origin main - Working tree must be clean:
git status --porcelain
- Must be on
-
Check version isn't already used
- Read current version from
pyproject.toml(line withversion = "...") - If new version equals current version, abort: "Version is already set."
- Check tag doesn't exist:
git tag -l v<version> - If tag exists, abort: "Tag v already exists."
- Read current version from
-
Build changelog entry from git history
- Find the latest tag:
git describe --tags --abbrev=0 - Get commits since that tag:
git log <last-tag>..HEAD --format='%s' - Get merged PRs since that tag:
gh pr list --state merged --base main --search "merged:>=$(git log -1 --format=%ci <last-tag> | cut -d' ' -f1)" --json title,number --limit 50 - From the commits/PRs, compose a changelog section with only
### Addeditems — user-facing features. Skip fixes, refactors, chores, docs-only changes, and CI changes. - Format:
## [X.Y.Z] - YYYY-MM-DD ### Added - **Feature name** — short description - **Feature name** — short description - Also prepare a compare link for the bottom of CHANGELOG.md:
[X.Y.Z]: https://github.com/Kayba-ai/agentic-context-engine/compare/v<prev>...vX.Y.Z
- Find the latest tag:
-
Present draft to user
- Show: new version, changelog entry, and the release note (same as changelog "Added" bullets)
- Ask: "Create this release?" with options: Yes, Edit (let me revise), Cancel
-
On approval — apply changes
- Update
pyproject.toml: replaceversion = "<old>"withversion = "<new>" - Insert the changelog entry in
CHANGELOG.mdafter line 7 (before the previous release) - Add the compare link at the bottom of CHANGELOG.md
- Stage files:
git add pyproject.toml CHANGELOG.md - Commit:
git commit -m "chore(release): bump version to <version>"
- Update
-
Tag and push
git tag v<version>git push origin main --tags
-
Create GitHub release
- Title:
v<version> - Notes: only the "Added" bullets from the changelog entry — short and clean, no preamble
- Append:
**Full Changelog**: https://github.com/kayba-ai/agentic-context-engine/compare/v<prev>...v<version> - Run:
gh release create v<version> --title "v<version>" --notes "<notes>" - This triggers
.github/workflows/publish.yml→ PyPI publish
- Title:
-
Report summary
Released v<version> - Commit: <short-hash> - Tag: v<version> - Release: <github-release-url> - PyPI: publishing via workflow (check Actions tab)
Error handling:
- If
ghis not installed: "GitHub CLI (gh) is required. Install it: https://cli.github.com" - If not authenticated: "Run
gh auth loginfirst." - If push fails: report error, keep local commit (user can retry)
- If
gh release createfails: show the error, suggest manual creation
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.
- 2mo ago First seen · 76 lines · 0 tokens per session scan A cdedb9ca7b0c
release is a command published in the GitHub repository kayba-ai/agentic-context-engine (2,608 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 971 tokens. 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.
release compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| releasekayba-ai/agentic-context-engine | Command | 2.6k | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| dream-applyconorbronsdon/agent-memory-kit | Command | 2 | 1mo ago | MIT | A | 20 | Claude Code |
| gsd:shipmrboups/xbrain | Command | 2 | 1mo ago | MIT | A | 18 | Claude Code |
| gsd:complete-milestonemrboups/xbrain | Command | 2 | 1mo ago | MIT | A | 16 | Claude Code |
| deployNickRomanek/clawbridge | Command | 23 | 19d ago | Apache-2.0 | A | 0 | Claude Code |
| guardarMazalucas/El-DT-Lightweight-Army | Command | 4 | yesterday | MIT | A | 0 | Claude Code |
| releasejuan294/cc-rpi | Command | 5 | 3d ago | MIT | A | 0 | Claude Code |