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.
npx agentmods add commands/alifanov/darkflow/add-issuegit 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/add-issue)<a href="https://agentmods.dev/commands/alifanov/darkflow/add-issue"><img src="https://agentmods.dev/badge/commands/alifanov/darkflow/add-issue.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 | $0.00019 | $0.00724 |
| Opus 5 | $0.00010 | $0.00362 |
| Sonnet 5 | $0.00004 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
add-issue 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 3d 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
Load the project config (contract in .darkflow.d/claude.md → Project config). Uses: language.
If $ARGUMENTS contains text (e.g. /darkflow:add-issue fix login button on mobile), use that text as the title — do not ask for a title again.
Walk through only the missing fields conversationally — skip any field already clear from the title:
-
What is it? (if not already clear) — bug, feature, or improvement? (just for your own framing — there's no separate type field)
-
Title (if not provided in $ARGUMENTS) — short action-oriented ("Fix X", "Add Y")
-
Priority:
- critical — breaks revenue or a key feature right now
- high — this week
- medium — this month
- low — someday / nice-to-have (allowed for manual tasks; scheduled routines never auto-create
low)
-
Description — "Briefly describe the problem and what done looks like." Use the answer to fill the body template from
docs/tasks.md→ Task body — the template: a## Problemparagraph, a## Planof 2–5 checkbox steps, and 1–3## Acceptance criteria— each one naming the command, report or URL that decides it. Do not ask the user for the plan: draft it yourself from the description and the code, and show it in the confirmation. Write the steps to be as independent as possible — each one lands on its own, leaves the project working, and could be done in a separate run; never make an early step depend on a later one, and merge two steps that only make sense together. If the work plainly does not fit one run (a migration, a refactor across many call sites), title the section## Plan (multi-run)instead —fix-issuesthen takes as many steps as fit per tick and closes the task once the last one lands. Default to the plain## Plan. -
Timing (only if the user mentioned a date/"not before" constraint) — add
--after <ISO date>to the create command so fix-issues won't pick the task up before that moment. Don't ask about this proactively.
Then construct and run:
~/.darkflow/df task create \
--title "<title>" \
--priority <p> --source manual --status approved \
--body "$(cat <<'EOF'
## Problem
<description>
## Plan
- [ ] 1. <first concrete step — the file to touch, the change to make>
- [ ] 2. <second step>
## Acceptance criteria
- [ ] <criterion 1 — with the command / report / URL that decides it>
- [ ] <criterion 2 if needed>
EOF
)"
Important rules:
- Language for all conversation and task text: the
languagevalue from.darkflow.d/state/config.json(default: English) - Always use
--status approved— the user already decided to do it - After creating, show the task number the command prints. The fix-issues routine will pick it up automatically.
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.
- 3d ago First seen · 54 lines · 19 tokens per session scan A 1172a134641b
add-issue is a command published in the GitHub repository alifanov/darkflow (2 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 724 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
project
Generate project documentation (product.md, structure.md, tech.md, codemaps/).
toh-help
Display all Toh Framework commands and quick usage guide.
feature
Create a feature specification using spec-driven development.
deep-audit.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Ornek cikti.
fix-issue
!gh issue view $ARGUMENTS 2>/dev/null || echo "Could not fetch issue $ARGUMENTS".
rev
Invoke Code Reviewer for code quality, security, requirements validation, and best practices review.