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/rule-effectivenessnpx skills add luiseiman/dotforge --skill rule-effectivenessgit 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 | $0.00024 | $0.01349 |
| Opus 5 | $0.00012 | $0.00674 |
| Sonnet 5 | $0.00005 | $0.00270 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
rule-effectiveness 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule Effectiveness Analysis
Analyze the effectiveness of .claude/rules/ in the current project by cross-referencing rule globs against actual file activity from git history.
Step 1: Collect rules inventory
Read all .md files in .claude/rules/. For each:
- Extract
globs:value from YAML frontmatter - Count lines of content (excluding frontmatter)
- Record filename and glob pattern
If a rule has no globs: or paths: frontmatter, classify as always-loaded (loads every session regardless of files touched).
Rules with globs: load eagerly at session start. Rules with paths: + alwaysApply: false load lazily (only when a matching file is touched). Note: paths: must be unquoted CSV — YAML arrays and quoted strings fail silently.
Step 2: Collect file activity from git history
Run: git log --name-only --pretty=format:'' --since='3 months ago' (or configurable period).
Parse output to build:
- session_files: group files by commit date (approximate 1 day = 1 session)
- total_sessions: count distinct dates with commits
- all_files_touched: unique set of all files modified
If fewer than 5 sessions available, warn that results may not be representative and extend to --since='6 months ago'.
Step 3: Cross-reference rules vs activity
For each rule with a glob pattern:
- Match glob against all_files_touched using bash glob expansion or fnmatch logic
- Calculate:
matched_files: count of unique files that match the globmatch_rate: % of sessions where at least 1 file matched the globtoken_cost: lines of rule content (proxy for context consumption)
For the project overall:
covered_files: files that match at least 1 rule globuncovered_files: files touched but matching no rulefile_coverage: covered / total
Step 4: Classify rules
| Classification | Criteria | Action |
|---|---|---|
| Active | match_rate > 50% | Keep — rule loads in most sessions and covers real files |
| Occasional | match_rate 10-50% | Evaluate — may be worth keeping for specific workflows (deploys, migrations) |
| Inert | match_rate < 10% | Candidate for removal — consumes tokens without matching real files |
| Always-loaded | globs: **/* or no globs |
Evaluate content — is it generic enough to justify always loading? |
| Overbroad | globs: **/* but content is stack-specific |
Should have narrower globs to avoid loading in wrong contexts |
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 · 133 lines · 24 tokens per session scan A 40e8e8a24174
rule-effectiveness is a skill published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 1,349 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
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.
prioritize
Pick 2–3 independent ops tasks from active plans and backlog for autonomous execution, weighing impact, feasibility, and project goals.
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…
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-auth
Auth and authorization conventions distilled across builds with three different auth stacks (Better Auth + orgs, Supabase Auth + RLS, Clerk). Covers the provider decision matrix, the unified wrapper interface (requireAuth / requireRole / withOrgContext), procedure tier stacking, session handling, OAuth callback…