Borrowing it
Nothing to install: this file belongs to saajunaid/caddis-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saajunaid/caddis-plugin/main/.github/instructions/validation-discipline.instructions.mdgit clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/instructions/saajunaid/caddis-plugin/validation-discipline)<a href="https://agentmods.dev/instructions/saajunaid/caddis-plugin/validation-discipline"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/validation-discipline/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/instructions/saajunaid/caddis-plugin/validation-discipline"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/validation-discipline.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 | $0.01168 | $0.01168 |
| Opus 5.5 | $0.00467 | $0.00467 |
| Sonnet 5.5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
caddis-plugin validation-discipline.instructions.md 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validation Discipline
These rules apply whenever an agent is asked to verify, validate, audit, or check the state of files, repositories, or system components. They exist to prevent two classes of error: declaring something missing when it exists, and declaring something clean when it has pending work.
Rule 1 — Confirm Absence With a Text Search
Never declare a file entry missing based solely on a paginated read_file scan.
read_file with line ranges can return truncated or empty results at range boundaries without indicating the file has more content. A "(empty)" return does not mean the target content is absent.
Required protocol:
- Before writing any FAIL verdict for a missing entry, run a
grep_search(orSelect-String) targeting the specific term. - An empty
grep_searchresult is definitive proof of absence. - A partial file read is not.
# ✅ CORRECT: confirm absence
Select-String -Path "docs\port-registry.md" -Pattern "my-service"
# Empty result = entry is absent. Non-empty = entry exists.
# ❌ WRONG: read lines 1-60, see nothing, declare absent
Rule 2 — Use the Primary Signal for Git Push Status
Never infer push status from git log --oneline -N decoration text or from git status.
The decorations (HEAD -> main, origin/main) in a short log are correct, but verifying by visual inspection under context load is error-prone. Dirty working tree output from git status is orthogonal to push status and must not be conflated with unpushed commits.
Required protocol:
- Use
git log origin/main..HEAD --onelineexplicitly. - Empty output = zero unpushed commits. Non-empty = commits to push.
git statusandgit diffanswer a different question (uncommitted changes) — do not use them as push-status signals.
# ✅ CORRECT: definitive push check
git log origin/main..HEAD --oneline
# Empty = nothing to push
# ❌ WRONG: infer from git status showing modified files
# ❌ WRONG: infer from visual inspection of ref labels in git log -3
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 · 109 lines · 1,168 tokens per session scan A c3fe398db214
caddis-plugin validation-discipline.instructions.md is an instructions file published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 1,168 tokens to every session, about $0.0047 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.