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/observability-checkgit 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/observability-check)<a href="https://agentmods.dev/commands/alifanov/darkflow/observability-check"><img src="https://agentmods.dev/badge/commands/alifanov/darkflow/observability-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 | $0.00018 | $0.01198 |
| Opus 5 | $0.00009 | $0.00599 |
| Sonnet 5 | $0.00004 | $0.00240 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
observability-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 4d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 1 — Read project config
Load the project config (contract in .darkflow.d/claude.md → Project config). Uses: language.
Step 2 — Do the work
Check the observability tool configured for this project (SigNoz, Datadog, Grafana, or equivalent). Specifically:
- Errors — new or spiking error rates in the last 24h; group by error type
- Slow endpoints — URLs with p95 latency > 1s; note the slowest 5
- Database queries — slow queries (> 100ms), N+1 patterns, queries without indexes, highest-volume queries per endpoint
- Request volume — unusual spikes or drops vs the previous 7-day average
- Integration health — are all services reporting? Any gaps in traces or missing spans?
For each finding:
- State the metric and its current value
- Compare to the previous period (yesterday / last week)
- Suggest a concrete fix (add index, cache result, paginate query, etc.)
Create a task for each significant finding. Use --source signoz (or the relevant observability tool) and a priority.
Auto-approve — additive index only. When the finding is purely adding a database index (no schema/data change, no query rewrite), create the task directly with --status approved instead of --status proposed, and add the line "Auto-approved — see docs/auto-approve.md." to the task body. This applies only to plain index additions — query rewrites, N+1 fixes, caching, denormalization, and any change that alters behavior or data stay --status proposed for human review.
Priority vocabulary: critical / high / medium / low. Only create tasks for critical / high / medium — low-priority findings are skipped (record them under Hypotheses in the snapshot instead).
Task format (required):
- Title: action-oriented verb — "Add index on X", "Cache Y endpoint", "Fix N+1 in Z" — never just a description of the symptom ("Slow endpoint detected", "High error rate on X")
- Body:
## Problem <metric, current value, comparison to previous period> ## Plan - [ ] 1. <concrete fix — specific table, query, endpoint, or config to change> - [ ] 2. <next step, if the fix needs one> ## Acceptance criteria - [ ] <measurable outcome, e.g. "p95 latency on /api/users drops below 500ms"> - [ ] <additional criterion if needed>
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.
- 4d ago First seen · 118 lines · 18 tokens per session scan A e8a9b455b729
observability-check is a command published in the GitHub repository alifanov/darkflow (2 stars, last pushed 5d ago), licensed MIT. It adds 18 tokens to every session and 1,198 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.