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 jeffreytse/grimoire-core --skill give-developmental-feedbackgit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/jeffreytse/grimoire-core/give-developmental-feedback)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/give-developmental-feedback"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/give-developmental-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/jeffreytse/grimoire-core/give-developmental-feedback"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/give-developmental-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 | $0.00044 | $0.01934 |
| Opus 5 | $0.00022 | $0.00967 |
| Sonnet 5 | $0.00009 | $0.00387 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade A, and why
give-developmental-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 6d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Give Developmental Feedback
Deliver specific, behavior-grounded feedback using the Situation-Behavior-Impact (SBI) model so the recipient can act on it immediately without becoming defensive.
Why This Is Best Practice
Adopted by: The CCL's SBI model is licensed to 750+ organizations globally including Google, Meta, Microsoft, and Cisco; Kim Scott's Radical Candor framework — built on the same behavioral-specificity principles — is used at Apple, Twitter, and Dropbox; Netflix's culture deck mandates candid, real-time peer and manager feedback as a non-negotiable operating principle across the entire organization Impact: Gallup's 2017 research (State of the American Workplace, 195k respondents) found employees who receive regular meaningful feedback are 3.6× more likely to be engaged than those who don't; CCL research documents that behavior-focused feedback using SBI reduces defensive reactions by 40–60% compared to judgment-framed feedback, because recipients can accept a description of behavior without feeling their identity is under attack; managers who give feedback in the moment — not batched into quarterly reviews — improve behavior correction speed by 8–12 weeks Why best: Vague feedback ("be more proactive", "good work") produces no behavior change because recipients cannot identify what to repeat or stop; annual performance review feedback arrives months after the event, making behavioral course-correction practically impossible; SBI grounds every piece of feedback in an observable event that both parties can agree happened, removing the subjectivity that makes feedback feel unfair
Sources: Center for Creative Leadership "Feedback That Works: How to Build and Deliver Your Message" (CCL Press, 2nd ed. 2014); Kim Scott "Radical Candor" (St. Martin's Press, 2017); Gallup "State of the American Workplace" (2017); Netflix "Culture" (culture.netflix.com)
Steps
1. Choose the right moment
Deliver feedback within 24–48 hours of the observed behavior. Beyond 48 hours, behavioral specificity degrades and the feedback feels retrospective rather than developmental.
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.
- 6d ago First seen · 138 lines · 44 tokens per session scan A 503545c1b609
give-developmental-feedback is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 21d ago), licensed MIT. It adds 44 tokens to every session and 1,934 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
giving-feedback
Structures effective feedback conversations using the Situation-Behaviour-Impact (SBI) model from the Center for Creative Leadership. Separates observable behavior from interpretation, anchors feedback in specific situations, and articulates concrete impact. Use when preparing difficult performance conversations…
coaching-techniques
GROW model, active listening, developmental feedback, and team growth approaches.
counseling-psychology
Therapeutic frameworks, assessment, ethical practice, and client documentation for counselors and psychologists.
cognitive-load
Don't overwhelm — chunk, scaffold, summarize first.
learning-psychology
Help humans learn through partnership, not instruction.
academic-paper-reviewer
Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on…