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/alifanov/darkflowWrote 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/alifanov/darkflow/checklist-review)<a href="https://agentmods.dev/commands/alifanov/darkflow/checklist-review"><img src="https://agentmods.dev/badge/commands/alifanov/darkflow/checklist-review.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 | $0.00020 | $0.01213 |
| Opus 5 | $0.00010 | $0.00607 |
| Sonnet 5 | $0.00004 | $0.00243 |
| Haiku 4.5 | $0.00002 | $0.00121 |
Grade A, and why
checklist-review 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 7d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scores this product against the readiness checklists shipped with Dark Flow — the accumulated knowledge of what the portfolio has already got wrong, grouped by discipline.
The other audit routines hunt for new findings. This one asks a narrower question: of the things we already learned the expensive way, which ones does this product still get wrong?
Report-only. No tasks are created, nothing is committed. The output is a score and a table.
Manual only. This is not a routine — no schedule, no catalog entry, no worker dispatch. It runs when a human asks for it, so the report is written to be read right now, in the terminal.
Step 1 — Read project config
Load the project config (contract in .darkflow.d/claude.md → Project config). Uses:
language, domain, stagingUrl.
Check stagingUrl when it is set, otherwise domain. Never take a step that writes real
data — no live payments, no real emails, no destructive account actions. Items that would
require one are n/a, and the report says which and why.
Step 2 — Resolve the group
$ARGUMENTS selects the group. Empty → all.
Valid: code, architecture, ux, seo, ads, security, analytics, ops, all.
Anything else: print the valid list and stop. Do not guess at what was meant.
Step 3 — Load the checklists
ls ~/.darkflow/checklists/
Read the .yml file for each selected group. Each carries two lists:
items— what must hold. Fields:id,severity,title,applies_when,check,source.never_flag— known false positives, verified not worth fixing.
If the directory is missing, say so and stop: this Dark Flow install predates the checklists, and re-running the installer fixes it. Never invent items. The checklists are the contract; a check that is not in them does not belong in this report.
Step 4 — Evaluate
For each item, decide applies_when first. If it does not apply, mark n/a and move on.
Then gather evidence and follow the item's check literally:
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.
- 7d ago First seen · 129 lines · 20 tokens per session scan A b2ec66465c9e
checklist-review is a command published in the GitHub repository alifanov/darkflow (3 stars, last pushed 8d ago), licensed MIT. It adds 20 tokens to every session and 1,213 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
lint-fix
Run all formatters and linters with auto-fix.
plan-swarm
Execute a plan file with parallel agent swarm (dependency-aware).
beads-swarm
Execute beads with parallel agent swarm (dependency-aware).
codemap-creator
Generate or update hierarchical code map from any directory as root, with nested tree structure (project).
implement-swarm
Implement from conversation context with parallel swarm.
plan-loop
Execute a plan file with iterative loop until completion.