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 agentmods add instructions/chuspeeism/dashi-taskboard/agents-mdgit clone --depth 1 https://github.com/chuspeeism/dashi-taskboardWhat 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 | $0.04315 | $0.04315 |
| Opus 5 | $0.02158 | $0.02158 |
| Sonnet 5 | $0.00863 | $0.00863 |
| Haiku 4.5 | $0.00432 | $0.00432 |
Grade A, and why
dashi-taskboard AGENTS.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 3d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Development Rules
For feature work in this repository, use this order:
- Before implementation, prove the real operation path to the user: entry point → user or agent action → data change or other side effect → observable result. Cite the actual component, API, and file involved, or demonstrate the path in the product. This proof is not a test.
- Implement the requested main path with the smallest direct change that makes it work.
- After implementation, demonstrate or verify only that direct operation path and give the result to the user for confirmation.
- Before the user confirms the feature works, do not proactively add guardrails, mutation or regression tests, legacy compatibility protection, defensive extensions, or speculative fallback behavior.
- User confirmation does not automatically authorize that follow-up work. Add targeted protection or tests only when the user explicitly asks for them, or when the user reports a concrete failure scenario that requires them.
The primary objective is to make the requested function work. Focus on the feature implementation itself and avoid over-design; safety, guardrails, and testing must not dominate the work or turn the feature into a surrounding engineering project.
This ordering does not waive higher-priority safety or security requirements. Keep validation that is necessary at real external boundaries, such as user input or external APIs, but do not expand it into hypothetical protection beyond the requested path.
Taskboard Delivery Workflow
Use this workflow when the user asks to process Taskboard work.
1. Read and claim work
- Read only the Taskboard states that the user asked to process. For the normal development flow, claim
todoitems and continue unfinishedin_progressitems. - Never assign
backlogitems. Leave an item unclaimed when its description or latest comment explicitly requires waiting. - Read the full issue description, attachments, and all comments before routing or changing it.
- GitHub Issue and PR synchronization is not a default step. Read or synchronize GitHub Issue/PR data only when the user explicitly requests it.
- Use the packaged or injected
taskctland the exact active Taskboard runtime. Do not fall back to a global CLI, a guessed port, or another data source.
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.
- 3d ago First seen · 196 lines · 4,315 tokens per session scan A af4333627cc5
dashi-taskboard AGENTS.md is an instructions file published in the GitHub repository chuspeeism/dashi-taskboard (2,853 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,315 tokens to every session, about $0.0216 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 2026-08-30.
Other instructions, from other repositories
codex-loop-orchestra AGENTS.md
Instructions for LEO001020/codex-loop-orchestra, covering loop discipline, 1. decomposition discipline (single-pass plan-and-solve), 3. return convention (all subagents, mandatory), 4. recoverable compression directive and 5. kernel trigger rules (ipybox, when enabled).
dev-flow AGENTS.md
Instructions for Innocent-children/dev-flow, covering dev flow repository instructions, authority, requirement scope, documentation and internationalization and product boundary.
codexbar-lite AGENTS.md
AGENTS.md instructions for wei-b0/codexbar-lite, covering agents.md, repo layout, commands, app notes and release gotchas.
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.
supergraph AGENTS.md
Instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
codex-third-party-subagents AGENTS.md
Instructions for dhy365-creator/codex-third-party-subagents, covering agents.md, project scope, rules for agents working here, layout and validation.