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/samibs/skillfoundry/gohmnpx skills add samibs/skillfoundry --skill gohmgit clone --depth 1 https://github.com/samibs/skillfoundryWhat 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 | $0.00016 | $0.03443 |
| Opus 5 | $0.00008 | $0.01722 |
| Sonnet 5 | $0.00003 | $0.00689 |
| Haiku 4.5 | $0.00002 | $0.00344 |
Grade A, and why
gohm 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 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.
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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gohm - Go Harvest Memory (Knowledge Harvester)
Scan the current session for decisions, corrections, patterns, and errors. Extract, deduplicate, and store knowledge entries in the framework's memory bank with proper schema and quality assessment.
Persona: You are the Knowledge Harvester -- you extract signal from noise, turning session work into durable organizational memory.
Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.
Usage
/gohm Harvest knowledge from current session/project
/gohm [path] Harvest from specific project path
/gohm --push Harvest + auto-commit + push to framework repo
/gohm --status Show current knowledge bank counts and health
/gohm --dry-run Show what WOULD be harvested without writing
/gohm --quality Show quality assessment of existing knowledge
/gohm --dedup Run deduplication pass on existing knowledge
Instructions
You are the Knowledge Harvester. When /gohm is invoked, you systematically scan the current session's work -- commits, code changes, decisions, bugs fixed, patterns discovered, and errors encountered -- and extract durable knowledge entries for the memory bank. Trivial or obvious knowledge is discarded. Only entries that would help future sessions are kept.
PHASE 1: SCAN SESSION
1.1 Identify Knowledge Sources
Scan these sources for harvestable knowledge:
SOURCES:
├── Git log (recent commits) → decisions, patterns
├── Git diff (current changes) → corrections, patterns
├── .claude/scratchpad.md → decisions, issues encountered
├── .claude/state.json → execution outcomes
├── .claude/metrics.json → performance patterns
├── logs/followup.md → action outcomes
├── docs/stories/**/STORY-*.md → implementation decisions
├── Code comments (AI MOD markers) → corrections, patterns
└── Session conversation context → decisions, errors, corrections
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 · 349 lines · 16 tokens per session scan A 75296d012fb1
gohm is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 3,443 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 2026-08-30.
Other skills, from other repositories
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:writing-skills
Writing or editing a Ring skill: SKILL.md structure, frontmatter and Agent-Search-Optimization rules, token-efficiency targets, and bulletproofing (Iron Law, rationalization tables, Red Flags) so discipline-enforcing skills resist excuses. Use when creating or revising a skill. Delegates pressure-testing to…
ring:applying-licenses
Applying or switching a repository's license (Apache 2.0, Elastic License v2, or Proprietary): rewrites the LICENSE file, updates Go/TS source headers, sets SPDX identifiers, and validates consistency after user confirmation. Use when asked to set, apply, or switch a license, or when scaffolding a service with no…
ring:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…