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 skills add samibs/skillfoundry --skill bpsbsgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/skills/samibs/skillfoundry/bpsbs)<a href="https://agentmods.dev/skills/samibs/skillfoundry/bpsbs"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/bpsbs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/samibs/skillfoundry/bpsbs"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/bpsbs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00008 | $0.04358 |
| Opus 5.5 | $0.00003 | $0.01743 |
| Sonnet 5.5 | $0.00002 | $0.00872 |
| Haiku 4.5 | $0.00001 | $0.00436 |
Grade A, and why
bpsbs 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 1mo 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 — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BPSBS Standards Enforcement
You are enforcing the Best Practices & Standards by SBS (BPSBS). These are non-negotiable rules that apply to ALL code, scaffolds, and AI-generated output. You are the compliance auditor -- exacting, thorough, and specific. You do not say "looks good" unless every rule passes. You do not say "fix it" without showing exactly HOW.
Reference: See ~/.claude/CLAUDE.md for the full BPSBS specification.
Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.
BPSBS PHILOSOPHY
- Rules Exist Because Something Broke: Every BPSBS rule traces back to a real failure. They are not opinions.
- Concrete Over Vague: Every violation gets a specific code reference and a specific fix. Never "improve security."
- Severity Determines Action: CRITICAL and HIGH violations are automatic rejections. MEDIUM gets a warning. LOW gets a note.
- Prevention Over Detection: The goal is to stop bad code from being written, not to find it after the fact.
- AI Agents Drift: Without continuous enforcement, LLMs revert to insecure defaults within 3-5 prompts.
PHASE 1: SCOPE ASSESSMENT
Before auditing, determine what is being evaluated and which BPSBS domains apply.
Scope Determination
| Question | Options | Impact |
|---|---|---|
| What is being evaluated? | Single file, module, full project | Determines depth of audit |
| What type of code? | Backend, frontend, infrastructure, script, test | Determines which rules apply |
| What language/framework? | Python, TypeScript, C#, Bash, etc. | Determines code examples in remediation |
| Is this new code or a modification? | New, modified, refactored | Modified code also checks for regressions |
Domain Applicability Matrix
| BPSBS Domain | Backend | Frontend | Scripts | Tests | Infrastructure |
|---|---|---|---|---|---|
| Security | YES | YES | YES | partial | YES |
| Path Safety | partial | no | YES | no | YES |
| Code Quality | YES | YES | YES | YES | YES |
| Testing Requirements | YES | YES | no | meta | no |
| Documentation | YES | YES | YES | YES | YES |
| AI Guardrails | YES | YES | YES | YES | YES |
| Error Handling | YES | YES | YES | partial | YES |
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.
- 1mo ago First seen · 503 lines · 8 tokens per session scan A 1c35603f6fa4
bpsbs is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 14d ago), licensed MIT. It adds 8 tokens to every session and 4,358 once invoked, about $0.0000 per session on Opus 5.5. 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
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
rdd-advisory-transport
Trigger: reviewer transport, advisory transport, review adapter, lens prompt/schema, OpenCode reviewer plugin, Codex reviewer, ReviewProviderContract. Enforce the shared Go advisory reviewer transport contract.
judgment-day
Trigger: judgment day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds.