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/boldergit clone --depth 1 https://github.com/Dragoon0x/canonWrote 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/dragoon0x/canon/bolder)<a href="https://agentmods.dev/commands/dragoon0x/canon/bolder"><img src="https://agentmods.dev/badge/commands/dragoon0x/canon/bolder.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 | $0.00017 | $0.00415 |
| Opus 5 | $0.00009 | $0.00208 |
| Sonnet 5 | $0.00003 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
bolder 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 3d 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
/bolder
Some interfaces are too quiet. They look unfinished, not refined. This command adds presence.
What this does
- Audit the current state. Is it truly timid, or is it quiet-done-well? Don't fix what isn't broken.
- Signs an interface is too timid:
- Every text color is the same near-black gray.
- All buttons look secondary.
- Headings barely distinguish from body.
- Brand color appears once, apologetically.
- Everything is 50% opacity.
- Apply the escalation ladder:
- Type scale: push the display sizes up. H1 goes from 32 to 48+. Weight on display elements moves from 600 to 700–800.
- Hierarchy gap: widen the contrast between heading and body. Different size, different weight, different color if warranted.
- Primary action: one primary button per screen, and it looks unmistakably primary. Filled, brand color, confident.
- Brand color: use it on primary actions, on focus rings, on one signature element. Not on every border.
- Negative space: sometimes bolder means more whitespace, not more ink. A huge quiet area around a single confident element is bolder than ten loud elements.
- Hold the line on CANON discipline:
- Still WCAG AA.
- Still 4/8 grid.
- Still semantic tokens.
- No skeuomorphic shadows, no neon glows, no 3D text effects.
Output
- Before/after side by side.
- Changes grouped: type, color, space, hierarchy.
- Rationale per change in one sentence.
Success criteria
The interface has a point of view. You can identify the primary action from 6 feet away. Headings feel like headings. The brand color earns its presence.
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.
- 3d ago First seen · 40 lines · 17 tokens per session scan A e34a8929ccf2
bolder is a command published in the GitHub repository Dragoon0x/canon (5 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 415 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.