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/zircote/rlm-rs/releasenpx skills add zircote/rlm-rs --skill releasegit clone --depth 1 https://github.com/zircote/rlm-rsWrote 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/zircote/rlm-rs/release)<a href="https://agentmods.dev/skills/zircote/rlm-rs/release"><img src="https://agentmods.dev/badge/skills/zircote/rlm-rs/release.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 | $0.00158 | $0.02950 |
| Opus 5 | $0.00079 | $0.01475 |
| Sonnet 5 | $0.00032 | $0.00590 |
| Haiku 4.5 | $0.00016 | $0.00295 |
Grade A, and why
release 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 4d 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.
curl -fsSL -A 'rlm-rs-release-check' \ How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rlm-rs Release Orchestration
Run a complete attested release for this repository. The argument is either
an explicit version (/release v1.4.0) or a bump type
(/release patch|minor|major), which computes the target from the current
Cargo.toml version. Every phase below ends with a verification; do not
proceed past a failure — fix it or stop and report.
The pipeline this skill drives (all already wired in .github/workflows/):
prep PR ──merge──> tag push ──┬─> release.yml (test + audit gates → 4 platform
│ binaries → provenance + SBOM attestations →
│ fail-closed verify → GitHub Release)
└─> publish.yml (pre-publish checks → crates.io
Trusted Publishing → download registry .crate
→ sha256 match → attest)
release.yml completion ─workflow_run─> package-homebrew.yml (formula update)
Help / no argument
If invoked with no argument, --help, or help, print this and stop —
do not start a release:
/release — attested release orchestration for rlm-rs
USAGE
/release v<X.Y.Z> release an explicit version (e.g. /release v1.4.0)
/release patch bump 1.3.1 -> 1.3.2 and release
/release minor bump 1.3.1 -> 1.4.0 and release
/release major bump 1.3.1 -> 2.0.0 and release
WHAT IT DOES
prep PR (5 version locations) -> required-checks green -> squash merge
-> annotated tag -> monitors: attested binaries + SBOM + fail-closed
verify -> GitHub Release; crates.io Trusted Publishing + .crate
attestation; Homebrew auto-update -> independent workstation
verification of every artifact.
NOTES
- Publishing to crates.io is irreversible; versions are immutable.
- CHANGELOG [Unreleased] must have content; empty means stop and ask.
- Never re-runs release.yml against an existing tag (asset immutability).
Phase 0 — Preflight
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.
- 4d ago First seen · 214 lines · 158 tokens per session scan A a4a836d29417
release is a skill published in the GitHub repository zircote/rlm-rs (57 stars, last pushed 4d ago), licensed MIT. It adds 158 tokens to every session and 2,950 once invoked, about $0.0008 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
rlm
The RLM pattern enables processing massive contexts (10M+ tokens) that exceed Claude's context window by recursively chunking, processing, and aggregating results. Instead of failing on large files, use RLM to break them into manageable pieces.
rlm
This skill should be used when the user asks to "process a large file", "analyze document exceeding context", "use RLM", "recursive language model workflow", "chunk and analyze a file", "handle long context", or needs to work with documents too large to fit in the context window. Orchestrates the full RLM loop using…
rlm-chunking
This skill should be used when the user asks about "chunking strategies", "how to chunk a file", "semantic vs fixed chunking", "chunk size selection", "overlap settings", or needs guidance on selecting the appropriate chunking approach for RLM processing.
Vector Databases
Guides retrieval-store design, indexing, and query behavior for embedding-backed systems without confusing storage with application truth.
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.