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/large-task-fidelity.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/large-task-fidelity)<a href="https://agentmods.dev/instructions/saajunaid/caddis-plugin/large-task-fidelity"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/large-task-fidelity/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/large-task-fidelity"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/large-task-fidelity.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 | $0.01880 | $0.01880 |
| Opus 5.5 | $0.00752 | $0.00752 |
| Sonnet 5.5 | $0.00376 | $0.00376 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
caddis-plugin large-task-fidelity.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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: "Large-task execution discipline — pre-flight scan, path gate, anti-drift rules, and equal-depth enforcement for multi-phase planning and implementation sessions" applyTo: ".github/agents/.agent.md, .github/instructions/.md, .github/plans/*.md"
Large-Task Fidelity Instructions
Apply these rules whenever a task produces a large, structured, multi-phase output — specifically:
- 4 or more phases in a single session
- 50 or more expected output lines
- Multiple reference documents attached as constraints
These are execution discipline rules, not requirements-gathering rules. They are orthogonal to plan-mode.instructions.md (which handles discovery and clarification before implementation begins). Apply both when a session moves from planning into large-scale output generation.
Trigger Conditions
Activate when the task involves:
- A complete project plan across many phases
- A large implementation spanning multiple files and layers
- Any output where fidelity to attached reference documents is critical
- Any output where the end of the document must match the quality of the beginning
Rule 1 — Pre-Flight Scan (Required Before Any Output)
Before writing any task line, phase section, or implementation block, produce a pre-flight summary in this format:
Phase N — [Name]: ~N tasks expected, depends on [phase numbers or "none"]
Produce all phases first. Do not start the main output until the pre-flight is complete.
Why: Forces a full scope read before output commitment. Prevents depth decay on later phases because the agent has already committed to an expected task count per phase.
Rule 2 — Named Output File
When producing a planning artefact or task list, write it to a named file — not just as chat output.
- Include the output file path in the prompt:
OUTPUT DESTINATION: <relative path> - The file is the deliverable. Chat output is secondary.
- If the session produces a task list, the file name should clearly identify it (e.g.
master-task-list.md,phase-3-plan.md).
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 · 171 lines · 1,880 tokens per session scan A f22a7f78825a
caddis-plugin large-task-fidelity.instructions.md is an instructions file published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 1,880 tokens to every session, about $0.0075 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.