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 fatihguner/foreman --skill giving-feedbackgit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/giving-feedback)<a href="https://agentmods.dev/skills/fatihguner/foreman/giving-feedback"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/giving-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/fatihguner/foreman/giving-feedback"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/giving-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.03137 |
| Opus 5 | $0.00040 | $0.01569 |
| Sonnet 5 | $0.00016 | $0.00627 |
| Haiku 4.5 | $0.00008 | $0.00314 |
Grade A, and why
giving-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 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.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Giving Feedback
Here is an uncomfortable truth: most of the feedback you have given in your career has been useless. Not malicious, not even poorly intentioned -- simply useless. "Great job on that presentation" teaches nothing. "You need to be more strategic" is a Rorschach test, not guidance. "I'm disappointed in your performance this quarter" is an emotional discharge dressed as management. The receiver walks away knowing something happened but unable to extract a single actionable insight. Meanwhile, the giver checks "gave feedback" off their mental list and wonders why nothing changes.
The problem is structural, not motivational. Most people want to give good feedback. They simply lack a method. The Situation-Behaviour-Impact (SBI) model, developed by the Center for Creative Leadership, provides exactly that: a rigorous structure that strips feedback of vagueness, projection, and judgment while preserving its essential content. SBI does not make difficult conversations easy. It makes them effective.
The Framework
The SBI Model: Three Components
Effective feedback consists of three elements, delivered in sequence. Each element serves a specific function, and omitting any one of them degrades the feedback's utility.
S -- Situation
Anchor the feedback in a specific time, place, and context. This eliminates ambiguity and prevents the receiver from wondering "which time?" or "what do you mean?"
- Weak: "In meetings, you tend to..."
- Strong: "In yesterday's product review meeting, when we were discussing the Q2 roadmap..."
The situation establishes shared ground. Both parties can agree on when and where the event occurred.
B -- Behaviour
Describe the observable behaviour -- what the person did, not what you infer about their character, motivation, or intelligence. Behaviour is factual and disputable; interpretation is subjective and inflammatory.
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 · 201 lines · 80 tokens per session scan A 6c6748f3e911
giving-feedback is a skill published in the GitHub repository fatihguner/foreman (48 stars, last pushed 4d ago), licensed MIT. It adds 80 tokens to every session and 3,137 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 2026-09-06.
Other skills, from other repositories
give-developmental-feedback
Use when a manager needs to deliver specific, in-the-moment developmental feedback to a direct report — separate from a formal performance review — to improve a behavior or reinforce a strength using observable evidence.
manager-as-coach
A management approach in which managers help people do their best work instead of only supervising them. It focuses on using strengths, removing obstacles, setting clear expectations, giving recognition, and keeping teams small.
instructional-coaching-conversation-guide
Generate a coaching conversation guide with questions, protocols, and follow-up actions for a teaching focus. Use when preparing for coaching sessions, mentoring, or peer feedback conversations.
apply-grow-coaching
Use when a manager wants to help a direct report solve a problem, develop a skill, or reach a goal through structured questioning rather than advice-giving — because telling people answers builds dependency while coaching builds self-sufficiency.
design-team-norms
Use when a team is forming, after a significant membership change, or when a recurring dysfunction suggests the team lacks shared agreements on how to work together — to co-create explicit norms covering communication, decision-making, conflict, and accountability.
apply-solicited-advice-discipline
Use when someone asks you a specific question, or when you're tempted to offer advice, opinion, or evaluation nobody asked for — answer exactly the scope of what was asked and no more, and don't volunteer advice or judgment unprompted, because unsolicited or over-scoped advice is systematically discounted and can…