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/plan-docs)<a href="https://agentmods.dev/commands/yourtechbud/coding-harness-config/plan-docs"><img src="https://agentmods.dev/badge/commands/yourtechbud/coding-harness-config/plan-docs/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/plan-docs"><img src="https://agentmods.dev/badge/commands/yourtechbud/coding-harness-config/plan-docs.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 | $0.00006 | $0.00587 |
| Opus 5.5 | $0.00002 | $0.00235 |
| Sonnet 5.5 | $0.00001 | $0.00117 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade A, and why
plan-docs 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.
What it actually says
You are planning documentation updates. The user has provided guidance on what to document.
<doc_guidance> $ARGUMENTS </doc_guidance>
<planning_steps>
-
Explore the current docs before planning:
- Inventory
docs/if it exists, including files and top-level directories. - Understand existing style, naming, placement, structure, and navigation.
- Identify duplication, stale organization, excessive root-level files, or unclear ownership only when relevant to the requested docs work.
- If
docs/engineering-guidance/exists, treat it as protected: acknowledge it in navigation planning but do not plan modifications inside it unless explicitly requested.
- Inventory
-
Plan the smallest useful documentation change:
- Prefer updating or consolidating existing docs when it improves findability or reduces duplication without losing details.
- Create new docs only when the topic needs a durable home or does not fit existing files.
- Preserve existing structure unless a structural change has clear value. Suggest moves, renames, merges, or new folders only when they materially improve navigation, reduce duplication, or clarify ownership.
- Root-level docs files are fine, but many unrelated ones suggest a clearer structure may help.
- Prefer minimal diffs; avoid rewriting unrelated sections.
- Recommend structure that fits this repo; do not force universal folders like
architecture/,journeys/, orproduct/. - Plan
docs/README.mdupdates when navigation or structure changes. Treat it as explaining how docs are organized, not just a flat index. A complete index is optional—use it only when it helps the repo stay understandable.
-
Output the full plan in chat with:
- Brief goal summary.
- Current docs observations that affected the plan.
- Files to create, with proposed purpose and headings/sections.
- Files to edit, with exact sections to add, revise, move, or trim.
docs/README.mdchanges, if any.- Structure changes, if any, with rationale.
- Major diffs to confirm: moves, renames, deletes, cross-file merges, or large restructures. Note how details will be preserved in any consolidation.
- Open questions that block execution.
-
End by inviting the user to revise the plan or approve implementation.
</planning_steps>
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 · 49 lines · 6 tokens per session scan A 769ae581b674
plan-docs is a command published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 6 tokens to every session and 587 once invoked, about $0.0000 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.