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 a1024053774/design-integrity-guardrails --skill reality-first-engineeringgit clone --depth 1 https://github.com/a1024053774/design-integrity-guardrailsWrote 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/a1024053774/design-integrity-guardrails/reality-first-engineering)<a href="https://agentmods.dev/skills/a1024053774/design-integrity-guardrails/reality-first-engineering"><img src="https://agentmods.dev/badge/skills/a1024053774/design-integrity-guardrails/reality-first-engineering/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/a1024053774/design-integrity-guardrails/reality-first-engineering"><img src="https://agentmods.dev/badge/skills/a1024053774/design-integrity-guardrails/reality-first-engineering.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 | $0.00046 | $0.00903 |
| Opus 5 | $0.00023 | $0.00451 |
| Sonnet 5 | $0.00009 | $0.00181 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
reality-first-engineering 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reality-First Engineering
Use this before architecture or broad implementation when a wrong assumption would cause meaningful rework, data loss, security exposure, irreversible side effects, or a false acceptance result. It is a small decision gate, not a second project manager, code review, test suite, or reason to delay a cheap reversible probe.
Do not use it for a small change with known inputs, contracts, and environment, or for documentation/formatting-only work.
Gate protocol
- State the decision. Write the goal, non-goals, acceptance condition, and the exact decision that must be made before implementation.
- Separate facts from guesses. Label each relevant item
observed,measured,inferred, orunknown. An implementation assumption is not evidence. For facts likely to change, record the source and verification date. - Choose the smallest probe. For each material unknown that could change the direction, define one falsifiable experiment with real inputs, a pass condition, a failure condition, a stop condition, an owner, and an evidence location. Test the highest-impact unknowns first; stop once the decision is determined instead of building the whole system to discover it.
- Gate the direction. Return
PASSonly when the architecture or plan follows from the available evidence.BLOCKED: a decisive input, authority, or probe is unavailable, or the evidence disproves the proposed direction; no safe direction can be chosen.INCOMPLETE: evidence exists but is partial or ambiguous; narrow to verified work or report what remains, and never silently treat it asPASS. Do not cover the gap with a fallback, compatibility path, mock-only branch, or speculative abstraction.
- Keep the boundary testable. Put external effects behind the existing boundary that owns them and keep deterministic domain/state logic driven by supplied inputs. A mock may validate pure logic, but it cannot establish an external fact it replaces. Add a layer only when a concrete caller or boundary needs it.
What ships with it
1 file 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.
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.
- 4d ago Changed · +7 lines · +4 tokens per session cf057d4cdc27
- 10d ago First seen · 77 lines · 42 tokens per session scan A 39080750db0f
reality-first-engineering is a skill published in the GitHub repository a1024053774/design-integrity-guardrails (0 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 903 once invoked, about $0.0002 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
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by OpenBitFun's unified Review mechanism instead.…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
pr-review-canvas
Create a OpenBitFun Canvas for reviewing a pull request, branch diff, or change set with Cursor-style diff cards, review maps, risk callouts, and focused reviewer flow. Use when the user asks for a PR review canvas, diff walkthrough, change-set overview, or visual review summary.