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 commands/dragoon0x/canon/adaptgit clone --depth 1 https://github.com/Dragoon0x/canonWhat 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 | $0.00021 | $0.00517 |
| Opus 5 | $0.00010 | $0.00259 |
| Sonnet 5 | $0.00004 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
adapt 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 2d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/adapt
Take a design that works at one breakpoint and make it work at all of them. Not "add a few media queries" — think about the content's shape, not the viewport's.
What this does
- Load
canon-responsive,canon-spatial,canon-interaction. - Identify the base viewport (where the design was built) and the actual range it needs to support.
- Work through each surface:
- Phone portrait (320–480px): single column, 16px gutters, bottom-sheet for heavy interactions.
- Phone landscape (480–768px): still single column, but reconsider fixed headers (they eat too much vertical).
- Tablet portrait (768–1024px): hybrid; sidebar may collapse, grid goes 2-column.
- Tablet landscape / small desktop (1024–1280px): multi-column settles in.
- Desktop (1280–1920px): intended layout.
- Wide (1920px+): cap container width, don't let lines of text stretch past 75ch.
- Container queries for components in variable containers (the sidebar card that also appears in a 12-col grid).
- Touch vs pointer:
- Wrap hover effects in
@media (hover: hover). Hover on touch devices sticks and looks broken. - Touch targets: 44×44px floor, 8px spacing between.
- Pointer: tighter spacing OK, but don't go below 24×24px for icon buttons.
- Wrap hover effects in
- Density modes (optional): compact / default / comfortable. Scale spacing, not font size, to change density.
- Dark mode: verify every color token has a dark-mode counterpart. Check contrast in both.
- Input modes: keyboard-only nav works end-to-end, focus-visible rings visible in both themes.
Output
- Breakpoint strategy in 3 sentences.
- Changes per breakpoint, specific.
- Any container queries introduced.
- Touch target audit.
- Dark mode verification note.
Success criteria
- No horizontal scroll at 320px.
- Nothing truncated awkwardly at 768–1024px (the "forgotten" range).
- Text never exceeds 75ch on ultra-wide.
- Touch targets hit 44px on phone.
- Keyboard nav works across all sizes.
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.
- 2d ago First seen · 45 lines · 21 tokens per session scan A b574de3bd596
adapt is a command published in the GitHub repository Dragoon0x/canon (5 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 517 once invoked, about $0.0001 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 commands, from other repositories
pm-status
Scan open PRs, report pipeline state, merge ready work to dev, and keep the staging promotion PR current.
review-pr
Fetch a pull request diff, run code-reviewer analysis, translate findings to owner voice, and post a single batched inline GitHub review.
codex-review
Run an adversarial review of the current branch via Codex (GPT-5.4). Default = direct Bash + thin + cheap; --verbose = wrapper-agent + 3x Opus burn.
halt-check
Smoke test — verify every hook and middleware respects the HALT kill switch. Advisory, read-only.
freeze
Activate the REA kill switch — writes .rea/HALT with a reason, blocking all governed tool calls until unfrozen.
review
Run the code-reviewer agent against the current branch's diff and produce structured findings.