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 rules/micsm/boffin/boffin-pack-routinggit clone --depth 1 https://github.com/MicSm/boffinWrote 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/rules/micsm/boffin/boffin-pack-routing)<a href="https://agentmods.dev/rules/micsm/boffin/boffin-pack-routing"><img src="https://agentmods.dev/badge/rules/micsm/boffin/boffin-pack-routing.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 | $0.01819 | $0.01819 |
| Opus 5 | $0.00910 | $0.00910 |
| Sonnet 5 | $0.00364 | $0.00364 |
| Haiku 4.5 | $0.00182 | $0.00182 |
Grade A, and why
boffin-pack-routing 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 6d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ParselFire Core Pack Activation
Default Workflow
First match scope to the task, then pick the path:
- Focused change (the operator asked for a specific function, fix, or feature): stay inside that scope. Make only the change requested, apply the stage guidance to what you touch, and prove it with a check. Do not scan the whole file or build a file-wide ledger; turning a scoped coding task into a file-wide refactor breaks the task boundary and gets rejected.
- Open-ended refactor, cleanup, or review of existing code: run the two-pass audit below, scoped to what the task covers.
Two-pass audit (refactor / review / cleanup). Never fix while you are still searching; the first strong improvement you find is not the finish line.
Pass 1, Audit (read-only). Read the target across the task's scope. Walk stages S00 upward and emit a findings ledger that covers every in-scope stage, including stages with nothing to change. Do not edit anything in this pass. Use one row per finding:
path | stage | status | id | kernel | anchor | check
Columns: path the file touched; stage the S00-S06 stage; status todo,
done, or skip; id the kernel id; kernel what it requires in one phrase;
anchor the concrete code location the finding rests on; check the test or
lint that proves it.
statusis one oftodo,done,skip, and everyskipcarries a reason.- Record every fix you name while auditing as its own row with all fields
filled, and resolve it as
doneorskip:<reason>; never leave a fix you mentioned in reasoning off the ledger. skip:cleanmeans Pass 1 found nothing on that stage; every in-scope stage still gets a row, never an omitted one.- A finding you deliberately will not act on is
skip:<reason>whose reason names the blocking kernel (for example, keeping a genuine special case instead of flattening it), neverskip:clean. - A row recorded as
todoresolves only todone(with its check) orskip:<reason>; never downgrade atodotoskip:clean.
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.
- 6d ago First seen · 107 lines · 1,819 tokens per session scan A b0e2224235cc
boffin-pack-routing is a cursor rule published in the GitHub repository MicSm/boffin (38 stars, last pushed 13d ago), licensed MIT. It adds 1,819 tokens to every session, about $0.0091 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 cursor rules, from other repositories
cursor_template
Enforcing engineering standards and governance in AI-First development through automated guardrails.
craft-skill
Create new bigpowers skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill for the bigpowers lifecycle.
grill-me
Interactive assumption-surfacing Q&A that stress-tests a plan through relentless questioning until every decision is resolved. Use when user wants to challenge a plan, validate decisions from conversation/context, or mentions "grill me". For doc-grounded variant, use grill-with-docs.
run-planning
DISCOVER-PHASE ADVANCER — Drive the discover-phase checklist (specs/planning-status.yaml) through survey-context → scope-work → research-first → elaborate-spec → plan-release → slice-tasks. NOT a duplicate of plan-work or the planning spine; it orchestrates the pre-coding discover phase only.
slice-tasks
PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work.
terse-mode
Fallback ultra-compressed communication mode. Cuts token usage 75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use ONLY when context is critically long and compressing output is necessary to continue. Not a strategy — token discipline comes from code shape (small functions…