Borrowing it
Nothing to install: this file belongs to tensorbee/rdocx. 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/tensorbee/rdocx/main/.claude/commands/realign-docs.mdgit clone --depth 1 https://github.com/tensorbee/rdocxWrote 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/tensorbee/rdocx/realign-docs)<a href="https://agentmods.dev/commands/tensorbee/rdocx/realign-docs"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/realign-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/tensorbee/rdocx/realign-docs"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/realign-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 | $0.00036 | $0.01162 |
| Opus 5.5 | $0.00014 | $0.00465 |
| Sonnet 5.5 | $0.00007 | $0.00232 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
realign-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 26d 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.
/realign-docs [--section NN] [--dry-run]
Repair accumulated documentation drift in bulk. /complete-feature updates the
HLD files one story's plan listed, which is right per story and insufficient
over a sprint. Decisions taken in review, alternatives rejected during
implementation, and scope that shifted mid-story do not appear in any single
plan's ## HLD impact list.
Run at a sprint close, at a milestone boundary, or after /sprint-review
surfaced a docs finding.
--dry-run reports the intended edits and changes nothing. Prefer it first.
The two hard rules
1. Grounded, never invented. Every sentence you write or change must trace to a citable source: a design plan, a review file, an AS_BUILT entry, or the code itself. If you cannot cite it, you do not know it, and a confident paragraph about behaviour nobody implemented is worse than the stale one it replaced.
2. Current state, never history. These documents describe what is true now.
Do not write "F-042 changed this from X to Y". Describe Y. Do not add a
"Changes in this milestone" heading. git log and docs/sprints/AS_BUILT.md
hold history, and a changelog inside an authoritative document is the first
sign it is rotting into one.
Steps
-
Establish the window. Everything since the last realignment, or since a named tag. Report the commit range and the F-IDs it contains.
-
Read the ground truth, in this order:
.claude/plans/F-XXX-design.mdfor each F-ID in the window, especially## Approach,## Rejected alternativesand## HLD impact..claude/reviews/for the same F-IDs, plus anySNN-sprint-review-*. Review files hold decisions that exist nowhere else, because a finding that was refuted with evidence is a decision.docs/sprints/AS_BUILT.mdentries in the window, especially the "Notes for future sessions" and the hash-harness fields.- The code, last. It settles any disagreement between the above.
-
Run
/audit-specand fold its findings in. This command is the actor for the drift that command reports.
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.
- 26d ago First seen · 106 lines · 36 tokens per session scan A 26b0c7e96b22
realign-docs is a command published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,162 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 2026-10-04.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
sync-linear
Sync current work with Linear ticket status.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.