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/vijayatechlabs/openstart/feedbackgit clone --depth 1 https://github.com/vijayatechlabs/openstartWhat 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 | $0.00373 |
| Opus 5 | $0.00009 | $0.00187 |
| Sonnet 5 | $0.00004 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
feedback 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 2d 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
You are running the OpenStart feedback flow for the current project.
Follow .ai/framework/FEEDBACK.md exactly. It is the canonical description of
the feedback pipeline.
Steps
-
Run the capture script with the user's message, type, and area:
bash .ai/framework/feedback.sh "<message>" [--type enhancement] [--area onboard]Pass any
--typeor--areaflags the user provided. If not provided, omit them (the script defaults toenhancement/general). -
Show the output — the local log path and the full issue text — so the user can review both before anything goes to GitHub.
-
Ask for confirmation before filing. Do NOT run
gh issue createautomatically. External writes require explicit user confirmation (seeAGENT-GUIDE.md §9guardrails). Ask:"Shall I file this as a GitHub issue on
vijayatechlabs/openstart?" -
If confirmed, run the
gh issue createone-liner thatfeedback.shprinted and report the returned issue URL.
Non-negotiable rules
- Never edit
.ai/framework/files to patch a framework gap — file feedback instead. - The local log (
.ai/docs/FRAMEWORK-FEEDBACK.md) is always written first; GitHub filing is secondary and requires confirmation. - If
feedback.shexits non-zero (empty message, missing file), report the error and ask the user to supply the missing information.
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.
- 2d ago First seen · 37 lines · 18 tokens per session scan A 53821dde0d2d
feedback is a command published in the GitHub repository vijayatechlabs/openstart (5 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 373 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
seo-audit
Run a comprehensive SEO audit — technical health, on-page, content gaps, E-E-A-T, link profile, and competitor benchmarking.
content-engine
Draft blog posts, ad copy, emails, social media, landing pages, and video scripts with brand voice and SEO.
performance-report
Generate a marketing performance report with KPI tracking, trend analysis, anomaly detection, and recommendations.
backlink-gap
Find domains linking to your competitors but not to you, ranked by priority score (DR + link-overlap + traffic + topical relevance) with a four-gate quality scorecard.
seo-drift
Compare two SEO snapshots (GSC / GSC AI Performance / rank tracker / AEO probe) and surface top movers per metric with auto-classification — growth / decline / reshuffle / stable / new / lost.
geo
Full GEO optimization pipeline - analyze, rank, rewrite, and generate schema for any URL or content.