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 commands/lets7512/rlm-skill/rlmgit clone --depth 1 https://github.com/Lets7512/rlm-skillWhat 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 | $0.00000 | $0.00375 |
| Opus 5 | $0.00000 | $0.00187 |
| Sonnet 5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
rlm scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **METADATA**: Assess file — type, size, lines, 200-char preview via `python3 -c` (or `python -c` on Windows). Use **glob** for file discovery (never `find`). **WebFetch is blocked** — download via python urllib instea What it actually says
Use the RLM 6-step structured protocol for this task. Instead of reading large data into context, explore it programmatically through: METADATA -> PEEK -> SEARCH -> ANALYZE -> SYNTHESIZE -> SUBMIT.
Key principle: Tokens are CPU, not storage. Never dump raw data into context.
For the user's request "$ARGUMENTS":
- METADATA: Assess file — type, size, lines, 200-char preview via
python3 -c(orpython -con Windows). Use glob for file discovery (neverfind). WebFetch is blocked — download via python urllib instead. Prefer python over PowerShell for data processing. - PEEK: Sample head/tail/random slices to understand structure
- SEARCH: Targeted extraction (regex, AST, JSON keys) based on PEEK findings
If file is 500KB+, continue with:
- ANALYZE: Decomposition — spawn @explore sub-agents per chunk (up to 15 sub-queries). Pass only the chunk + specific question to each sub-agent.
- SYNTHESIZE: Combine findings, cross-reference, resolve conflicts
- SUBMIT: End with explicit SUBMIT block:
=== RLM SUBMIT ===
Query: [question]
Confidence: [high/medium/low]
Protocol: [steps executed]
Sub-queries: [N spawned, N completed]
Data processed: [size]
[Answer]
=== END ===
If data is 50MB+ — use rlm-cli query "..." --file <path> --stats
Budget: 20 iterations max, 15K chars/step, 15 sub-queries max. Always SUBMIT.
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.
- 2d ago First seen · 32 lines · 0 tokens per session scan A 07bb6c3678ed
rlm is a command published in the GitHub repository Lets7512/rlm-skill (24 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 375 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.