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/rhtevan/agentfs/skill-harvestnpx skills add rhtevan/agentfs --skill skill-harvestgit clone --depth 1 https://github.com/rhtevan/agentfsWrote 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/rhtevan/agentfs/skill-harvest)<a href="https://agentmods.dev/skills/rhtevan/agentfs/skill-harvest"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/skill-harvest.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 5.1 | $0.00015 | $0.04485 |
| Opus 5 | $0.00008 | $0.02243 |
| Sonnet 5 | $0.00003 | $0.00897 |
| Haiku 4.5 | $0.00002 | $0.00449 |
Grade A, and why
skill-harvest 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 526 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Harvest — Memory-to-Skill Distillation
Scope guard: This skill is not available in LITE scope projects. LITE scope does not support skills or knowledge bundles. If the target project's AGENTS.md contains
agentfs-scope: lite, refuse with a clear message.
Harvest procedural knowledge from project-scoped MEMORY.md files and
distill them into reusable skills under ~/.agents/skills/.
This skill completes the graduation path defined in AgentFS
Guardrail #2 (Memory Scope & Signal Routing), targeting procedural memory — the counterpart to
okf-bundle-harvest which handles declarative/semantic knowledge.
When episodic memories accumulate into repeatable action sequences, graduate them into skills — idempotent, executable workflows that any agent can load and follow.
How It Relates to Other Harvest Skills
| Aspect | okf-bundle-harvest |
skill-harvest |
|---|---|---|
| Target memory type | Semantic (concepts, patterns) | Procedural (workflows, SOPs) |
| Output format | OKF concept documents (.md) | SKILL.md + scripts/ |
| Output location | ~/.agents/knowledge/ |
~/.agents/skills/ |
| Graduation signal | "This is a generalizable truth" | "This is a repeatable action sequence" |
| Scope | USER only (knowledge) | USER by default (skills) |
| Idempotency | N/A (documents) | Preferred (scripts) |
Prerequisites
- At least one project with AgentFS set up (
.agents/directory) - MEMORY.md files with accumulated entries
- Write access to
~/.agents/skills/ - The
okf-bundle-genskill must be available (scanner script reused)
Fixed Configuration
| Setting | Value |
|---|---|
| Default output root | ~/.agents/skills/ |
| Skill format | SKILL.md + scripts/ + references/ |
| Entry delimiter | § (or timestamp-headed sections) |
Usage
Harvest from current project
harvest skills from project memories
Scans ./.agents/memories/ and ./.agents/profiles/*/memories/ in
the current working directory.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 526 lines · 15 tokens per session scan A 039620b873c9
skill-harvest is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 15 tokens to every session and 4,485 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…