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/spillwavesolutions/wiki_ticket_sdd/claude-mdgit clone --depth 1 https://github.com/SpillwaveSolutions/wiki_ticket_sddWrote 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/spillwavesolutions/wiki_ticket_sdd/claude-md)<a href="https://agentmods.dev/instructions/spillwavesolutions/wiki_ticket_sdd/claude-md"><img src="https://agentmods.dev/badge/instructions/spillwavesolutions/wiki_ticket_sdd/claude-md.svg" alt="Measured on agentmods" 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 | $0.01502 | $0.01502 |
| Opus 5 | $0.00751 | $0.00751 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
wiki_ticket_sdd CLAUDE.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 5d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acme Platform
Work tracking policy
Work items live in .work/todo.jsonl. Settings live in .work/config.yml — read that
file; do not infer settings from this document. This file is policy only, which is why
AGENTS.md is a symlink to it: one policy, every harness. Do not add harness-specific
notes here.
-
Every request that produces work is broken into worklog items FIRST. Run
bin/worklog add(see the work-track skill) before starting, and move itemsin_progress→doneas the work happens — the UserPromptSubmit and Stop hooks enforce this. Unrecorded work is invisible work. -
Exiting plan mode is not optional bookkeeping. Every plan MUST end by running
worklog plan-capture, which writesdocs/plans/<date>-<name>.mdand appends the plan's steps as work items. This is also enforced by a hook; if you find yourself ending a plan without it, that's a bug, not a shortcut. After capture, plans and their items are published (tickets + wiki) by a background subagent; implementation never waits on publishing. -
Plans are the permanent design record.
docs/plans/is where the why lives — it is the specification half of spec-driven development, checked into the repo and published to the wiki for exactly that reason. A plan is written once and never regenerated or rewritten. If the design changed, write a NEW plan withsupersedes: <slug>in its front matter. Do not edit history: the record of why the first approach was abandoned is the most valuable thing in the file. When you need to know why a decision was made, read the plan, not the ticket. -
If you discover work mid-flight that wasn't in the plan — a bug, a missing migration, a broken test — run
worklog add --unplanned --discovered-during <item>BEFORE doing the work. Do not silently absorb it. Unplanned work that never gets recorded is why estimates never improve. -
When a plan is complete, run
worklog sync. This closes items, updates the ticketing system, regenerates the roadmap, and publishes. Partial failure is expected and fine — sync is best-effort by design and reports its drift.
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.
- 5d ago First seen · 106 lines · 1,502 tokens per session scan A 9d884c8a5169
wiki_ticket_sdd CLAUDE.md is an instructions file published in the GitHub repository SpillwaveSolutions/wiki_ticket_sdd (10 stars, last pushed 2d ago), licensed MIT. It adds 1,502 tokens to every session, about $0.0075 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 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.