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 sliamh11/Deus --skill learn-proceduregit clone --depth 1 https://github.com/sliamh11/DeusWrote 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/sliamh11/deus/learn-procedure)<a href="https://agentmods.dev/skills/sliamh11/deus/learn-procedure"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/learn-procedure/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/sliamh11/deus/learn-procedure"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/learn-procedure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 11 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 157 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
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 | $0.00065 | $0.02633 |
| Opus 5.5 | $0.00026 | $0.01053 |
| Sonnet 5.5 | $0.00013 | $0.00527 |
| Haiku 4.5 | $0.00006 | $0.00263 |
Grade B, and why
learn-procedure scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
that could later be obeyed as instructions ("ignore previous instructions", "now run X"). If a Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/learn-procedure
Capture a repeatable task-execution procedure from the work just completed in this conversation and persist it as a memory node the assistant recalls automatically in future sessions. The pain this solves: multi-step task workflows (e.g. "rename a folder of images to each user's email using the roster .xlsx") get re-derived from scratch every session because nothing durable remembers the steps.
A procedure is stored as a normal memory-tree node with kind: procedure. It surfaces
through the existing UserPromptSubmit recall hook — no new retrieval path — when a
future prompt's intent matches the procedure's description.
Relationship to /learn-this and /preserve (read this — single source of truth)
/learn-this→ teaches the USER a topic and records what they LEARNED ($VAULT/Learning/)./preserve→ silently saves preferences/decisions/facts about the user ($VAULT/CLAUDE.md)./learn-procedure→ saves a HOW-TO the ASSISTANT should re-run: an executable, step-based task workflow (the auto-memory dir'sprocedures/subdir — see step 1).
Never duplicate the same content across these. A procedure is steps-to-execute, not a fact
about the user and not a lesson for the user. If a procedure relates to a learning record,
link with a see_also edge — do not copy.
When to use
Invoke after finishing a multi-step task that is likely to recur, where re-deriving the
steps next time would be wasteful. Do NOT capture one-off requests, trivial single commands,
or facts/preferences (those go to /preserve).
Steps
1. Resolve the auto-memory directory
A procedure is stored in the auto-memory directory — the same dir memory_indexer
promotes atoms into and that memory_query reads node content back from (LIA-341). Resolve it
with the shared resolver (never hardcode a path):
DEUS_HOME=$(deus root) || { echo "deus not on PATH" >&2; exit 1; }
python3 -c "import sys; sys.path.insert(0,'$DEUS_HOME/scripts'); from auto_memory_dir import resolve_auto_memory_dir; print(resolve_auto_memory_dir())"
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 · 196 lines · 65 tokens per session scan B 3776730c9de3
learn-procedure is a skill published in the GitHub repository sliamh11/Deus (52 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 2,633 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
handoff
Generate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps — so a fresh Claude session can continue exactly where this one left off. Use when sessions are getting long, Claude keeps retrying the same broken solution, or the user wants to step away and resume later.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…
brain_dump
Capture unstructured thoughts and organize them into structured notes saved to memory.
identity-snapshot
Generate a living profile of the user's working patterns, decision tendencies and quality preferences from their Dex data. Use when the user says 'what are my patterns', 'how do I work', or during week-review. Also use proactively when the model (older than 7 days) is stale. Not for planning a week; use week-plan.
nav-compact
Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits.
contextstream-coach
Coach this agent on work the person needs again and again, such as a weekly note, an article, a recap or an image series. Use it when the person starts a job for one of their workflows, reacts to a draft, or asks what was learned from earlier jobs. Goals, drafts and the person's own words are saved in their…