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 Bluestep-Systems/bspecs --skill bluestep-referencegit clone --depth 1 https://github.com/Bluestep-Systems/bspecsWrote 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/bluestep-systems/bspecs/bluestep-reference)<a href="https://agentmods.dev/skills/bluestep-systems/bspecs/bluestep-reference"><img src="https://agentmods.dev/badge/skills/bluestep-systems/bspecs/bluestep-reference/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/bluestep-systems/bspecs/bluestep-reference"><img src="https://agentmods.dev/badge/skills/bluestep-systems/bspecs/bluestep-reference.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 | $0.00083 | $0.07271 |
| Opus 5.5 | $0.00033 | $0.02908 |
| Sonnet 5.5 | $0.00017 | $0.01454 |
| Haiku 4.5 | $0.00008 | $0.00727 |
Grade A, and why
bluestep-reference 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- b6p-platform.md 13 KB
- bsjs-development.md 22 KB
- conventions/date-format.md 3.0 KB
- conventions/deploy-lib-workflow.md 4.8 KB
- conventions/endpoint-approach.md 814 B
- conventions/formula-patterns.md 3.9 KB
- conventions/mcp-platform-authoring.md 38 KB
- conventions/no-global-dollar.md 885 B
- conventions/separate-files.md 2.2 KB
- conventions/single-script.md 5.0 KB
- conventions/top-level-const-tdz.md 2.9 KB
- conventions/ts-in-template-literal.md 5.1 KB
- gotchas/b-exports-proxy-map.md 1.9 KB
- gotchas/common-gotchas.md 6.5 KB
- gotchas/connected-relationship-fields-inspector.md 2.4 KB
- gotchas/document-library-folder-keys.md 1.9 KB
- gotchas/fetched-resource-code.md 859 B
- gotchas/field-access-writability.md 5.1 KB
- gotchas/field-ids-not-portable-across-propagation.md 2.2 KB
- gotchas/meetscriteria-formula-context.md 2.2 KB
- gotchas/merge-report-editability-is-component-level.md 2.9 KB
- gotchas/merge-report-primary-form-required.md 1.9 KB
- gotchas/option-field-dom-value.md 1.9 KB
- gotchas/read-relatescript-source.md 1.6 KB
- gotchas/relate-query-over-mefr.md 3.3 KB
- gotchas/third-party-lib-type-noise.md 2.8 KB
- gotchas/unpublished-presave-draft-blocks-component.md 2.6 KB
- gotchas/viewurl-is-javascript-call.md 2.0 KB
- gotchas/vite-merge-report-gotchas.md 5.9 KB
- reference/ai-services.md 8.6 KB
- reference/api-patterns.md 22 KB
- reference/b-include-element.md 2.6 KB
- reference/chronounit-months.md 1.7 KB
- reference/client-side-form-api.md 2.9 KB
- reference/code-patterns.md 8.7 KB
- reference/component-library.md 8.8 KB
- reference/crm-dashboard-inspo.md 2.7 KB
- reference/csv-parsing.md 2.3 KB
- reference/current-record-bindings.md 4.0 KB
- reference/dashboard-design-system.md 2.3 KB
- reference/datetime-field-write.md 1.7 KB
- reference/design-system.md 6.2 KB
- reference/dpn-dashboard-framework.md 4.0 KB
- reference/endpoint-method-call.md 690 B
- reference/endpoint-no-delete-method.md 1.1 KB
- reference/endpoint-output-channel.md 1.9 KB
- reference/endpoint-urls.md 1.4 KB
- reference/entry-delete.md 1.8 KB
- reference/fid-alternate-identifier.md 4.7 KB
- reference/file-execution.md 5.7 KB
- reference/git-site-spa.md 11 KB
- reference/http-requester.md 1.8 KB
- reference/id-full-vs-short.md 1.3 KB
- reference/import-scope.md 3.2 KB
- reference/internal-loopback-fetch.md 2.3 KB
- reference/localdate-parse.md 723 B
- reference/mcp-read-multi-entry-forms.md 2.4 KB
- reference/merge-report-async-loading.md 3.8 KB
- reference/merge-report-entry-id-patch.md 2.2 KB
- reference/merge-report-memo-json.md 3.0 KB
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 Changed · +9 lines 61e10530f7d6
- 1mo ago First seen · 102 lines · 83 tokens per session scan A 56c1d4ab3030
bluestep-reference is a skill published in the GitHub repository Bluestep-Systems/bspecs (3 stars, last pushed yesterday), with no licence file. It adds 83 tokens to every session and 7,271 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
erlang-otp-behaviors
Use when oTP behaviors including genserver for stateful processes, genstatem for state machines, supervisors for fault tolerance, genevent for event handling, and building robust, production-ready Erlang applications with proven patterns.
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
axiom-concurrency
Use when writing ANY async code, actors, or threads in an Apple-platform app, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.
haskell-pro
Expert Haskell engineer specializing in advanced type systems, pure functional design, and high-reliability software. Use PROACTIVELY for type-level programming, concurrency, and architecture guidance.
splitting-oversized-modules
Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…
migrate-better-result-3
Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.