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/luiseiman/dotforge/forge-behaviornpx skills add luiseiman/dotforge --skill forge-behaviorgit clone --depth 1 https://github.com/luiseiman/dotforgeWhat 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 | $0.00046 | $0.00911 |
| Opus 5 | $0.00023 | $0.00456 |
| Sonnet 5 | $0.00009 | $0.00182 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
forge-behavior 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge behavior
Thin wrapper around scripts/forge-behavior/cli.sh. Dispatches behavior
governance actions. This skill is part of dotforge v3 (Phase 1 of behavior
governance) and should only be used inside dotforge itself or projects that
have adopted v3 — not on v2.9 projects.
When to use
Invoke this skill when the user asks any of:
- "What behaviors are active?"
- "What's the counter on search-first?"
- "Disable search-first for this session"
- "Turn off the nudge on writes"
- "Make search-first stricter / more relaxed"
Do NOT invoke this skill for v2.9 configuration tasks (use /forge audit,
/forge sync, etc.) or for behaviors that have not yet been catalogued
(Phase 1 only ships search-first).
Actions
scripts/forge-behavior/cli.sh status [--session SESSION_ID]
scripts/forge-behavior/cli.sh on <behavior_id> [--project | --session SESSION_ID]
scripts/forge-behavior/cli.sh off <behavior_id> [--project | --session SESSION_ID]
scripts/forge-behavior/cli.sh strict <behavior_id>
scripts/forge-behavior/cli.sh relaxed <behavior_id>
status — Print the current catalogue (behaviors/index.yaml) plus a
per-session summary from .forge/runtime/state.json: counters, effective
levels, override counts, pending_block status, and any session-scope
overrides.
on / off — Toggle a behavior's active state.
--project(default): mutatesbehaviors/index.yaml. Persistent. After changing, recompile the behavior withscripts/compiler/compile.sh behaviors/<id>/behavior.yaml <output_dir>and restart Claude Code so the new hook registration takes effect.--session SESSION_ID: mutates only.forge/runtime/state.json'sbehavior_overrides[]for that session. The compiled hook short-circuits silently when disabled. No recompile needed. Effect lasts until the session is purged by TTL.
strict / relaxed — Mutate behaviors/<id>/behavior.yaml escalation:
strict: halves eachafterthreshold, minimum 1. Makes violations escalate sooner.relaxed: doubles eachafterthreshold. Makes violations escalate later.- Both project-scope only in v1. Session-scope strictness deferred to
Phase 2 — the runtime would need to pass a strictness multiplier into
forge_resolve_level, which v1 does not support.
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 · 100 lines · 46 tokens per session scan A 536f51e47562
forge-behavior is a skill published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 911 once invoked, about $0.0002 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
scaffold
Set up or align a non-code ops/PM repo with the ops folder structure, CLAUDE.md, and INDEX.md hierarchy.
find-opps
Find new directions for an ops project — adjacent opportunities, strategic gaps, preparatory research. Use when known work is well-mined and you need to look outward.
factory-db-migration
The operational discipline for running a destructive change against a production database — schema migrations, data backfills, one-shot RPCs, historical seed imports. Adjacent to factory-data-layer.md (schema design) and factory-deployment.md (where migrations execute in CI) — this skill is about the runbook around…
prioritize
Pick 2–3 independent ops tasks from active plans and backlog for autonomous execution, weighing impact, feasibility, and project goals.
factory-api
API conventions for both server actions and tRPC builds. Covers the decision between them, per-mutation Zod input schemas, central router composition, pagination shape, multi-field search via Drizzle ilike + or(), mutation lifecycle hooks, conditional query enabling, stale-time defaults, error response shape and…
factory-ci
CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…