Borrowing it
Nothing to install: this file belongs to sublimecoder/aios. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sublimecoder/aios/main/.claude/commands/open-flags.mdgit clone --depth 1 https://github.com/sublimecoder/aiosWrote 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/sublimecoder/aios/open-flags)<a href="https://agentmods.dev/commands/sublimecoder/aios/open-flags"><img src="https://agentmods.dev/badge/commands/sublimecoder/aios/open-flags/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/sublimecoder/aios/open-flags"><img src="https://agentmods.dev/badge/commands/sublimecoder/aios/open-flags.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 | $0.00040 | $0.00210 |
| Opus 5.5 | $0.00016 | $0.00084 |
| Sonnet 5.5 | $0.00008 | $0.00042 |
| Haiku 4.5 | $0.00004 | $0.00021 |
Grade A, and why
open-flags 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 1mo 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
Read and follow Mode B of AIOS/Skills/open-flags.md — the standalone sweep.
Arguments: $ARGUMENTS — an optional layer (creator / professional / work) or a
project name to scope the sweep. One layer at a time; never synthesize across layers.
Mode A already runs inside every /aios-ingest (step 1e) and is bounded by that run's
evidence. This is the other half: the flags no ingest's evidence happens to touch.
Rows go to AIOS/History/audits/flag-register.md, not the Log — one Log line per
aged flag per run would refill the file log-rollup exists to keep lean.
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.
- 1mo ago First seen · 16 lines · 40 tokens per session scan A b598aafe9254
open-flags is a command published in the GitHub repository sublimecoder/aios (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 210 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-19.
Other commands, from other repositories
linear-drain
Create the queued Linear projects and issues that shell scripts captured offline.
ingest
Compile new sources from raw/ into the wiki.
lint
Repair broken wikilinks, orphans, and duplicate articles.
query
Answer a question from the wiki and save it to outputs/.
pm-autoplan
Orchestre les trois angles de revue (stratégie, utilisateur, faisabilité) en parallèle, puis synthétise leurs pages de stress-test dans output/.
pm-epic-01-happy
Un PRD complet est disponible dans output/ : il contient des exigences P0/P1 avec des critères d'acceptation et une section ## Métriques de succès. Le pm-decomposer crée un epic avec ## Success Criteria et des issues enfants P0/P1 avec critères d'acceptation. Les issues sont liées à l'epic.