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 run-underperformance-conversationgit 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/run-underperformance-conversation)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/run-underperformance-conversation"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-underperformance-conversation.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.02428 |
| Opus 5 | $0.00027 | $0.01214 |
| Sonnet 5 | $0.00011 | $0.00486 |
| Haiku 4.5 | $0.00005 | $0.00243 |
Grade A, and why
run-underperformance-conversation 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 5d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Underperformance Conversation
Have an early, direct conversation the first time a performance gap appears — naming the specific gap, exploring causes without assuming, and agreeing on a clear path to correction — before the pattern hardens and requires formal process.
Why This Is Best Practice
Adopted by: Kim Scott's "Radical Candor" framework — used at Google, Dropbox, Apple, and most major tech companies as a management training standard — defines "challenging directly" as the non-negotiable second half of caring management; Linda Hill's research (100 new managers over one year, "Becoming a Manager") found that failure to address underperformance early was the single most common management failure among new managers, and that delay consistently made the situation worse; SHRM's early performance intervention framework is the HR industry standard for preventing PIPs through proactive management Impact: SHRM research found that managers who addressed underperformance within the first 30 days of observing it resolved the issue (returned the employee to expected performance) 70% of the time; managers who waited more than 90 days resolved it only 25% of the time; Gallup's 2022 research found that only 29% of employees "strongly agree" that their manager discusses their performance clearly — meaning 71% of employees are not getting early performance signal they need to course-correct; Kim Scott's framework identifies manager silence as "ruinous empathy" — the most common management failure, where concern for the employee's feelings causes the manager to withhold feedback that would actually help them Why best: Early underperformance conversations feel uncomfortable to managers — they require naming a gap to someone who may not see it, react defensively, or feel demoralized; managers avoid them through rationalization ("it's just a phase," "they're going through something personal," "it'll get better on its own"); this avoidance is the primary cause of formal PIP processes — by the time a PIP is needed, the gap has been growing for months while the manager said nothing; a single direct conversation at the first sign of decline is almost always easier for both parties than a formal documented process six months later
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.
- 5d ago First seen · 160 lines · 54 tokens per session scan A b9e44f07b634
run-underperformance-conversation is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 20d ago), licensed MIT. It adds 54 tokens to every session and 2,428 once invoked, about $0.0003 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
saga-orchestration
Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building…
meeting-efficiency
Agenda design, time boxing, decision capture, async alternatives, and productive facilitation.
deep-work-optimization
Focus blocks, distraction management, and flow state triggers for cognitively demanding work.
make-skill-template
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional…
disagreement-protocol
Canonical phrasing for respectful disagreement without capitulation — structural resistance to sycophancy.
fix-once-auto-inject
One-time fixes get repeated manually.