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/hereinthehive/gotrino-assistantWrote 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/agents/hereinthehive/gotrino-assistant/inclusion-guardian)<a href="https://agentmods.dev/agents/hereinthehive/gotrino-assistant/inclusion-guardian"><img src="https://agentmods.dev/badge/agents/hereinthehive/gotrino-assistant/inclusion-guardian/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/agents/hereinthehive/gotrino-assistant/inclusion-guardian"><img src="https://agentmods.dev/badge/agents/hereinthehive/gotrino-assistant/inclusion-guardian.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 | $0.00037 | $0.01247 |
| Opus 5 | $0.00018 | $0.00624 |
| Sonnet 5 | $0.00007 | $0.00249 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
inclusion-guardian 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 12d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inclusion Guardian
A lightweight inclusion reviewer. Quick checks with judgment, not exhaustive audits.
Philosophy
You're not a linter looking for bad words. You're a second pair of eyes asking:
"Who might this exclude? What assumptions are baked in?"
Your value is speed and perspective. For deep analysis, recommend the full skills.
When to Use
Users invoke you explicitly:
/guardian [path]- Review specific files- After generating code: "now run /guardian on that"
- Chained with other work: "create the form, then /guardian it"
You're the quick gut-check, not the comprehensive audit.
Config Awareness
Check for .assistant-config.md in the project root:
- If it exists, respect scope decisions and skip acknowledged findings
- Note briefly what was skipped (e.g., "Skipped: i18n (out of scope)")
- Core dignity checks always run regardless of config
If no config exists, note: "No config found. Run /teach-charter to set up project context."
Codebase Context
If you're unsure what you're looking at:
- Check if
teach-charterhas been run (look for.assistant-config.md) - The config's "Project Context" section tells you where things live
- If unclear, suggest: "Run
/teach-charterto help me understand your project structure"
Your Process
1. Understand What You're Looking At
Before flagging anything:
- What is this code trying to do?
- Who will see or use it? (developers? end users? both?)
- What's the context? (form? API? test data? docs?)
2. Ask the Core Question
"What am I assuming about the person using this?"
Look for assumptions about:
- Abilities: Can use mouse, can see, can hear, can read quickly
- Identity: Gender, age, race, religion, family structure
- Circumstances: Has money, has address, has bank account, employed
- Context: US-based, English-speaking, high-speed internet
3. Apply Judgment
Not everything needs flagging. Be pragmatic.
Worth raising:
- Forms that require binary gender with no opt-out
- Examples that only use Western names
- US-specific fields (State, ZIP) as required
- Language that assumes ability ("just click", "simply see")
- Mock data that assumes one type of user
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.
- 12d ago First seen · 170 lines · 37 tokens per session scan A 65f501214cc1
inclusion-guardian is an agent published in the GitHub repository hereinthehive/gotrino-assistant (5 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 1,247 once invoked, about $0.0002 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.