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/trumb/claude-nginx-hardeningWrote 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/trumb/claude-nginx-hardening/manage-exceptions)<a href="https://agentmods.dev/commands/trumb/claude-nginx-hardening/manage-exceptions"><img src="https://agentmods.dev/badge/commands/trumb/claude-nginx-hardening/manage-exceptions/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/trumb/claude-nginx-hardening/manage-exceptions"><img src="https://agentmods.dev/badge/commands/trumb/claude-nginx-hardening/manage-exceptions.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 | $0.00016 | $0.00704 |
| Opus 5 | $0.00008 | $0.00352 |
| Sonnet 5 | $0.00003 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
manage-exceptions 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 9d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Exception files: !
ls learnings/exceptions/*.md 2>/dev/null | wc -lexceptions found - Expired: !
python3 -c " import os, datetime from pathlib import Path count = 0 for f in Path('learnings/exceptions').glob('*.md'): content = f.read_text() for line in content.split('\n'): if line.startswith('review_by:'): date_str = line.split(':',1)[1].strip() try: if datetime.date.fromisoformat(date_str) < datetime.date.today(): count += 1 except: pass print(count) " 2>/dev/null || echo "0"expired exceptions
Operating Mode
DEFAULT: R0 + R1
With --apply: W1 (writes exception files)
Subcommands
list
Show all exceptions grouped by status:
- Active — within review_by date
- Expiring Soon — within 30 days of review_by (critical: 90 days)
- Expired — past review_by date
Display: exception_id, finding_id, severity_tier, owner, review_by, days remaining.
Color coding:
- Critical approaching expiry: prominent warning
- High approaching: warning
- Expired critical: BLOCKED indicator
- Expired high/low: warning indicator
create
Interactive exception creation:
- Show recent findings (from latest run outputs)
- User selects finding to except
- Prompt for reason (required, must be non-empty)
- Prompt for compensating control (required, must be non-empty)
- Auto-suggest severity_tier based on finding severity
- Prompt for owner (required)
- Prompt for approval_reference (ticket, PR, or doc reference)
- Prompt for review_by date (suggest 90d/180d/365d options, max 365 days)
- Run
python3 scripts/schema-validator.py --type exception --file <path>to validate - On pass: write exception file to
learnings/exceptions/ - Add inline comment to linked config:
# nginx-hardening: excepted EXC-NNNN — see learnings/exceptions/ - Append to CHANGELOG.md
review <exception-id>
Show full exception details. Prompt: renew, remove, or keep as-is.
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.
- 9d ago First seen · 84 lines · 16 tokens per session scan A ef84dfb12ff6
manage-exceptions is a command published in the GitHub repository trumb/claude-nginx-hardening (2 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 704 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
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.