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 skills/mayank-io/mstack/apply-feedbacknpx skills add mayank-io/mstack --skill apply-feedbackgit clone --depth 1 https://github.com/mayank-io/mstackWhat 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 | $0.00078 | $0.01224 |
| Opus 5 | $0.00039 | $0.00612 |
| Sonnet 5 | $0.00016 | $0.00245 |
| Haiku 4.5 | $0.00008 | $0.00122 |
Grade A, and why
apply-feedback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are reviewing a document that contains feedback comments tagged with one or more configured prefixes (e.g., [MK], [REV]). Tags and their interpretation rules are configured per-user in ~/.mstack/dev/feedback-tags.json.
Step 0: Load feedback tag configuration
Run this bash to check for the config file:
mkdir -p ~/.mstack/dev
CONFIG=~/.mstack/dev/feedback-tags.json
if [ -f "$CONFIG" ] && [ -s "$CONFIG" ]; then
cat "$CONFIG"
else
echo "MISSING"
fi
If output is MISSING (first run)
-
Create the file with the default
MKentry. Use the Write tool to write~/.mstack/dev/feedback-tags.jsonwith this content:{ "tags": [ { "tag": "MK", "from": "Document author (initials = MK for Mayank)", "content": "Direct edit instructions, factual corrections, rephrasing requests, structural changes", "action": "Apply edits as written; treat as imperative; only push back if ambiguous" } ] } -
Tell the user verbatim:
Saved your feedback tag config to
~/.mstack/dev/feedback-tags.json. Pre-seeded withMKas the default. Edit this file directly to add, modify, or delete tags later. -
Use AskUserQuestion: "Want to add another tag now? You can also add more later by editing the file." with options:
- A) No, continue with MK
- B) Yes, add another tag
-
If the user picks B, ask 4 questions in sequence (one AskUserQuestion call each, free-text answers):
- "What tag prefix? (short uppercase letters only — e.g., REV, FB, TODO. Will be matched case-insensitively in documents.)"
- "Who are these comments from? (e.g., 'External reviewer')"
- "What do these comments typically contain? (e.g., 'Suggestions and open questions')"
- "What action should I take with these comments? (e.g., 'Treat as suggestions; flag for discussion before applying')"
Read the current config, append the new tag object to the
tagsarray, write the updated file. Then ask "Add another?" again — loop until user says no.
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 · 112 lines · 78 tokens per session scan A dc4b8b9026d7
apply-feedback is a skill published in the GitHub repository mayank-io/mstack (5 stars, last pushed 8d ago), licensed MIT. It adds 78 tokens to every session and 1,224 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…