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.
git clone --depth 1 https://github.com/YourTechBud/coding-harness-configWrote 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/commands/yourtechbud/coding-harness-config/brainstorm-engineering-guidance)<a href="https://agentmods.dev/commands/yourtechbud/coding-harness-config/brainstorm-engineering-guidance"><img src="https://agentmods.dev/badge/commands/yourtechbud/coding-harness-config/brainstorm-engineering-guidance/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/commands/yourtechbud/coding-harness-config/brainstorm-engineering-guidance"><img src="https://agentmods.dev/badge/commands/yourtechbud/coding-harness-config/brainstorm-engineering-guidance.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 | $0.00019 | $0.00962 |
| Opus 5.5 | $0.00008 | $0.00385 |
| Sonnet 5.5 | $0.00004 | $0.00192 |
| Haiku 4.5 | $0.00002 | $0.00096 |
Grade A, and why
brainstorm-engineering-guidance 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 2mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You help me converge on a small, durable set of engineering guidance docs for this repo. Explore the repo and any relevant docs before proposing anything.
What I want to work on
$ARGUMENTS
Goal
Converge on a small, coherent guidance system under docs/engineering-guidance/, with README.md as the canonical entry point. Use my intent above as the spine of the conversation — what I want to work on drives the direction; the seed knowledge below is here so we don't rediscover it from scratch.
Seed knowledge
Draw on these aggressively as inspiration — adapt, tighten, or omit to fit the repo. They are starting points, not requirements.
<seed_principles>
- optimize for future change
- preserve boundaries
- prefer deep modules over shallow fragmentation
- keep surfaces legible and signal-rich
- prefer local reasoning
- make contracts explicit
- actively look for opportunities where shared components, functions, or modules could reduce behavioral, visual, or logic drift without weakening readability, boundaries, or local reasoning
- keep behavior honest and visible
- concentrate complexity intentionally
- verification should match risk
- favor navigability
- review failure semantics and graceful degradation
- review diagnosability and runtime visibility
- treat end-user experience as a first-class engineering concern when changes affect product behavior
- make completed work easy for humans to review and trust
- prefer clean internal interfaces over compatibility shims when callers can be migrated safely
- preserve compatibility deliberately at real user, data, integration, public API, or deployment boundaries
- discuss logging and observability expectations based on repo risk and runtime needs
- review trust boundaries and privilege exposure lightly
- scrutinize new package dependencies lightly </seed_principles>
<seed_lenses>
- architecture, modules, and boundaries
- modularity, reuse, and drift prevention
- state, effects, and runtime behavior
- user experience and product behavior
- refactoring, interface evolution, and backward compatibility
- logging, observability, and diagnosability
- reviewability and confidence-building artifacts </seed_lenses>
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.
- 2mo ago First seen · 81 lines · 19 tokens per session scan A b441abe2c2cc
brainstorm-engineering-guidance is a command published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 19 tokens to every session and 962 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.