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/vyuh-labs/dxkit/allowlistgit clone --depth 1 https://github.com/vyuh-labs/dxkitWhat 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 | $0.00000 | $0.03829 |
| Opus 5 | $0.00000 | $0.01914 |
| Sonnet 5 | $0.00000 | $0.00766 |
| Haiku 4.5 | $0.00000 | $0.00383 |
Grade A, and why
allowlist 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vyuh-dxkit allowlist
Per-finding suppression with a typed-category audit trail. The allowlist is dxkit's deliberate escape hatch for findings you can't fix today: false positives, intentional test-fixture patterns, real risks mitigated externally, or work you're deferring with an explicit deadline.
The principle: easier than disabling dxkit, harder than actually
fixing the issue. Every allowlist entry carries a typed category,
a required reason, and (when relevant) an expiry. Reviewers see new
entries in the PR comment automatically; the audit subcommand
surfaces stale + soon-to-expire entries for periodic cleanup.
When to use this command
Use the allowlist when fixing isn't viable today and the finding deserves explicit acknowledgement rather than silent suppression. Common scenarios:
- False positive: the scanner is wrong about this specific
finding. Allowlist with
category=false-positive+ a reason describing why. Bonus: consider reporting the false positive viavyuh-dxkit issueso the team can improve the rule. - Intentional test fixture: the "secret" is a placeholder API
key in a test file, or the SAST finding is in a deliberately-bad
example. Allowlist with
category=test-fixture. - Mitigated externally: a dep-vuln is real but the attack vector
is blocked by a WAF rule, network policy, or runtime guard.
Allowlist with
category=mitigated-externally+ a reason describing the mitigation. - Accepted risk: the team has reviewed the finding and accepts
it for now. Allowlist with
category=accepted-risk+ an explicit--expiresdate. The expiry forces re-review when the deadline passes. - Deferred fix: the work is tracked elsewhere (a ticket, a
next-sprint plan). Allowlist with
category=deferred+ an--expiresmatching the deadline.
If you find yourself reaching for the allowlist many times for the
same scanner rule, that's signal — open a --type=false-positive
or --type=missing-finding issue (see vyuh-dxkit issue)
so the team can tune the underlying detection.
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 · 357 lines · 0 tokens per session scan A 2889df5ea6d7
allowlist is a command published in the GitHub repository vyuh-labs/dxkit (10 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,829 tokens. 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
brooks-audit
Run a Brooks-Lint architecture audit.
dispatch-worker
Run one in-session-agent Worker tick (RFC-0041 §4.3.1).
todo
The quality-gated task list: tasks with real descriptions, testable acceptance criteria, and evidence — a task only closes when the controller agrees it is done.
security
The security pass: secrets (blocking), SAST, dependency vulns — plus the index's entry points to review from.
init
Install the formatters this repository needs, with every command visible before it runs.
research
Research a technical or product question.