Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Syedomershah99/being-humannpx agentmods add commands/syedomershah99/being-human/checkWrote 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/syedomershah99/being-human/check)<a href="https://agentmods.dev/commands/syedomershah99/being-human/check"><img src="https://agentmods.dev/badge/commands/syedomershah99/being-human/check.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 5.1 | $0.00012 | $0.00353 |
| Opus 5 | $0.00006 | $0.00177 |
| Sonnet 5 | $0.00002 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
check 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 6d 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
Score this for AI tells: $ARGUMENTS
If it's a file path:
python3 scripts/slopscore.py "$ARGUMENTS" --in .being-human/
If they pasted text instead, write it to a scratch file first and score that.
Then work through the output with them:
- Lead with the score and what it means. Above 85 reads human, below 50 is slop, in between is a draft with tells.
- Take the structural findings first — rhythm, paragraph shape, bullet symmetry. Those matter more than any single word, and fixing them changes how the whole piece reads. A draft can have zero flagged phrases and still be obviously generated because every sentence is the same length.
- Then the phrase-level hits, grouped rather than listed one by one.
- If
.being-human/metrics.jsonis missing, the thresholds were generic. Say so — the em dash and exclamation checks are only meaningful against their measured baseline, and a generic run will flag people who legitimately use both.
Offer to fix it rather than just reporting. If they say yes, rewrite and score again — don't hand back an unverified revision.
One thing to hold to: fix the writing, not the score. Swapping flagged words for unflagged synonyms raises the number without making the text any more theirs. If a passage is generic because it has nothing specific in it, the fix is a specific detail, and if you don't have one, ask.
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.
- 6d ago First seen · 37 lines · 12 tokens per session scan A 38cdc407ac91
check is a command published in the GitHub repository Syedomershah99/being-human (0 stars, last pushed 23d ago), licensed MIT. It adds 12 tokens to every session and 353 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.