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 matrixorigin/memoria --skill releasegit clone --depth 1 https://github.com/matrixorigin/memoriaWrote 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/matrixorigin/memoria/release)<a href="https://agentmods.dev/skills/matrixorigin/memoria/release"><img src="https://agentmods.dev/badge/skills/matrixorigin/memoria/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/skills/matrixorigin/memoria/release"><img src="https://agentmods.dev/badge/skills/matrixorigin/memoria/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.00567 |
| Opus 5.5 | $0.00011 | $0.00227 |
| Sonnet 5.5 | $0.00005 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00057 |
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 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.
What it actually says
Flow
| Step | Who | How |
|---|---|---|
| Bump version, tag, push | You | make release VERSION=x.y.z |
| Build binaries (4 platforms) | CI | release-rust.yml |
| Build + push Docker image | CI | release-docker.yml |
| Create GitHub Release | CI | softprops/action-gh-release |
Stable Release
git status # Must be clean
make release VERSION=0.2.0
Does: update Cargo.toml version → cargo check → generate CHANGELOG (git-cliff) → commit → tag → push.
CI then: test → build binaries (x86_64/aarch64 linux/macos) → GitHub Release → Docker image (:0.2.0 + :latest).
Pre-Release
make release-rc VERSION=0.2.0-rc1
Same but: no CHANGELOG, GitHub Release marked prerelease, Docker gets :0.2.0-rc1 (not :latest).
Typical: rc1 → rc2 → stable.
Manual Docker Push
make release-docker # :latest
make release-docker VERSION=0.2.0 # :0.2.0 + :latest
CI Workflows
| Workflow | Trigger | What |
|---|---|---|
test.yml |
Push main/develop, PRs | check + clippy + tests |
pr-title.yml |
PR open/edit | Conventional Commits validation |
release-rust.yml |
Tag v* |
Test → build → GitHub Release |
release-docker.yml |
Tag v* |
Test → build → Docker Hub |
Both release workflows run full test suite before publishing.
Version Locations
memoria/Cargo.toml— source of truthmemoria --version— binarymcp.json—_versionfield- Steering rules —
<!-- memoria-version: x.y.z -->
Checklist
- Clean working tree, CI green on main
- README/docs updated for user-facing changes
- Steering rules updated if tool behavior changed
-
make release VERSION=x.y.z - Verify GitHub Release has 4 binaries + checksums
- Verify Docker Hub has new tag
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 · 69 lines · 27 tokens per session scan A ae5264a77201
release is a skill published in the GitHub repository matrixorigin/memoria (614 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 567 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
github-ops
GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.
public-plugin-packaging
Use when packaging an Agentlas agent repo for public GitHub release, Codex plugin submission, Claude adapter distribution, or one-line terminal installation.
release-new-version
Use when the user wants to release a new Zafiro version — drafting bilingual release notes, deciding the next version number, bumping app/build.gradle.kts, tagging, and publishing to GitHub (main repo, optionally the Xposed repo).
parallel-pr-review
Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
release-sync
PromptHub release update skill. Use for /update-readme, version bumps, changelog updates, website sync, GUI screenshot/doc refresh, and multilingual release/documentation alignment.