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/mtthsnc/tempest/bcpnpx skills add mtthsnc/tempest --skill bcpgit clone --depth 1 https://github.com/mtthsnc/tempestWhat 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 | $0.00118 | $0.00934 |
| Opus 5 | $0.00059 | $0.00467 |
| Sonnet 5 | $0.00024 | $0.00187 |
| Haiku 4.5 | $0.00012 | $0.00093 |
Grade A, and why
bcp 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bcp — bring a Brand Context Protocol into the work
Overview
The bridge from this software factory to BCP (Brand Context Protocol) — a git-native standard
where a brand is written down as cited, dated truth that humans and AI agents build from, so
output is on-brand by construction and carries a trace. BCP lives in its own repo
(github.com/mtthsnc/bcp); this skill scaffolds it into a project and drives its skills. It does not
reimplement BCP — the brand repo is the source of truth, owned by you, not locked in tooling.
This is a STARTER skill — a generic spine. Rewrite the scaffold source and the per-deliverable flow to match how your business runs.
Procedure
1. Find or create the brand
- Look for an existing BCP in the project: a
harness/brand/tree (optionally withharness/config.json). - If none exists and brand work is needed, scaffold one: fetch the template into a brand repo,
e.g.
git clone --depth 1 https://github.com/mtthsnc/bcp <brand-dir>(ornpx degit mtthsnc/bcp <brand-dir>), setbrand.nameinharness/config.json, and run its./install.shto wire the BCP skills for pi and Claude Code. Work from the brand repo root so itsAGENTS.md/CLAUDE.mdand skills load.
2. Capture or extend Brand Truth
- Drive BCP's
brand-truthskill: turn raw input (interviews, audit, existing assets) into cited, dated truths inharness/brand/— positioning (01-imprint), voice + refusals (02-voice), design tokens (03-design), lenses, architecture. Append-only; supersede, never overwrite.
3. Produce a deliverable
- Use a BCP contract skill (e.g.
landing-page) to generate the asset intoharness/output/<slug>/with atrace.mdciting the truth ids it used. Draw only from Brand Truth — if a fact is missing, add it viabrand-truthfirst rather than inventing it.
4. Check before shipping
- Run BCP's
brand-checkskill to score the output against the brand (cited violations, written back to the trace, logged to09-loops), and run./scripts/brand-check.shfor the structural gate. - Recurring conflicts become proposed new truths/refusals + a dated decision — human-approved.
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 · 57 lines · 118 tokens per session scan A 9674d5b30fb0
bcp is a skill published in the GitHub repository mtthsnc/tempest (2 stars, last pushed 2mo ago), licensed MIT. It adds 118 tokens to every session and 934 once invoked, about $0.0006 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
codebase-memory
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions…
using-pi-subagents
Operate pi-subagents jobs safely, including direct-work decisions, least-privilege tool selection, thinking-level selection, delegation, bidirectional messaging, parallel starts, timeout selection, waiting, cancellation, result handling, verification, and writer isolation.
improvement-discovery
Heuristics and process for discovering structural improvements in this package. Load when planning a new improvement round — contains the smell taxonomy, analysis workflow, and prioritization framework distilled from many phases of refactoring.
fabric-workflow
Runs a dynamic Pi Fabric workflow with code-held phases, fan-out, pipelines, structured agents, and best-effort verification. Use for large audits, migrations, parallel research, or explicit workflow requests.
fabric-spec
Starts a persistent Pi Fabric spec supervisor that audits the main session against a feature design spec and steers only when a requirement lacks verified evidence. Use for strict, unblocked spec compliance while the main agent keeps full freedom to orchestrate.
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.