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 skills add samkawsarani/sams-product-plugins --skill give-feedbackgit clone --depth 1 https://github.com/samkawsarani/sams-product-pluginsWrote 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/skills/samkawsarani/sams-product-plugins/give-feedback)<a href="https://agentmods.dev/skills/samkawsarani/sams-product-plugins/give-feedback"><img src="https://agentmods.dev/badge/skills/samkawsarani/sams-product-plugins/give-feedback/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/samkawsarani/sams-product-plugins/give-feedback"><img src="https://agentmods.dev/badge/skills/samkawsarani/sams-product-plugins/give-feedback.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00100 | $0.01438 |
| Opus 5.5 | $0.00040 | $0.00575 |
| Sonnet 5.5 | $0.00020 | $0.00288 |
| Haiku 4.5 | $0.00010 | $0.00144 |
Grade A, and why
give-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 2mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What this skill does
Takes a raw reaction ("their Slack posts are too long", "great job today") and rebuilds it into feedback the recipient can act on based on SBIR framework, the Anatomy of High-Impact Feedback, and Radical Candor.
The core standard: If the person receiving the feedback doesn't know exactly what to do differently next time, the feedback wasn't instructional enough.
Step 1: Get the raw material
If the user hasn't already given it, ask for both in one message:
- What happened — the specific situation and behavior (not "they're disorganized" — what did they do).
- Who it's for + the relationship — direct report, peer, or someone more senior. This sets the Radical Candor framing.
If they only have a vague label ("not a team player", "bad at meetings"), pull the concrete moment out of them — the feedback can't be built without one observable behavior anchored in time. Don't proceed on a generalization.
Skip the interrogation if they've already supplied a situation + behavior. Bias for drafting.
Step 2: Classify — constructive or positive
Both use SBIR. Don't sandwich them together: keep praise and criticism in separate conversations, each gets its own space.
- Positive feedback is not "great job." Generic praise is noise. It must be instructional — tell them the exact behavior to repeat and why it mattered.
- Constructive feedback communicates a change you want to see.
Step 3: Build it in SBIR
Draft the feedback across four parts:
| Part | What goes here | Test |
|---|---|---|
| S — Situation | Anchor it. "In yesterday's client demo at 2pm…" | No generalities. A specific time/place. |
| B — Behavior | Observable actions only. "You interrupted the client twice." | NOT interpretation ("you were rude"). Could a camera have recorded it? |
| I — Impact | The effect that behavior had. "The client went quiet and we lost the pitch's momentum." | Ties the behavior to a real consequence. |
| R — Request | What you'd like next time, OR a question inviting their view. "Can you help me understand what was happening?" / "Next time, can we lead with the status?" | Gives a path forward or opens collaboration. |
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.
- 2mo ago First seen · 103 lines · 100 tokens per session scan A 9aebe0cb93a5
give-feedback is a skill published in the GitHub repository samkawsarani/sams-product-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,438 once invoked, about $0.0004 per session on Opus 5.5. 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.
give-feedback compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| give-feedbacksamkawsarani/sams-product-plugins | Skill | 2 | 1mo ago | MIT | A | 100 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |