Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add gtapps/hermitd/plugin install hermitd-fitnessWrote 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/gtapps/hermitd/weekly-coaching-patterns)<a href="https://agentmods.dev/skills/gtapps/hermitd/weekly-coaching-patterns"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/weekly-coaching-patterns/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/gtapps/hermitd/weekly-coaching-patterns"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/weekly-coaching-patterns.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 | $0.00049 | $0.01319 |
| Opus 5.5 | $0.00020 | $0.00528 |
| Sonnet 5.5 | $0.00010 | $0.00264 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
weekly-coaching-patterns 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 11d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weekly Coaching Patterns
Routine skill: reads the last 4 compiled/activity-*.md artifacts for steady sessions and detects whether cardiac drift is trending upward over time. Returns a fixed findings block for reflect --check-id weekly-coaching-patterns --check hermitd-fitness:weekly-coaching-patterns to classify and route.
Contract: idempotent, read-only, no self-scheduling, short-running. Returns findings or silence — never creates proposals itself.
Steps
-
Run the trend check. Issue a single Bash call:
bun ${CLAUDE_PLUGIN_ROOT}/scripts/fitness-lab.ts weekly-patternsThe script does the whole deterministic pass — filesystem only, no Strava token: globs
.hermit/compiled/activity-*.md, keeps entries whose frontmatter hastype: activity-noteANDsession_kind: steady, takes the 4 most recent bycreated, reads each note's signed drift from thecardiac_drift_bpmfrontmatter field, falling back to the body'sCardiac drift:line for notes written before that field existed (neither present → excluded; a negative value compares as smaller than any positive — the sign is never stripped), and evaluates a strict oldest-to-newest monotonic rise across all 3 adjacent pairs. It emits:{"steady_sessions_found": <int>, "series": [{"file": "…", "date": "…", "drift": <signed int>}], "trend": "upward" | "none" | "insufficient-data"}seriesis ordered oldest-to-newest.trend: "upward"means the 4-value bpm series is strictly increasing (the deliberately strict v1 bar — avoids false positives from noisy week-to-week variation)."none"= 4 values but not monotonic;"insufficient-data"= fewer than 4 drift values (expected on interval/strength-heavy weeks — not an error).Anti-duplication guard: emit a finding ONLY on
trend: "upward"(the quantitative numeric rise). Do NOT emit on label recurrence alone. -
Output the findings block. Always output a plain-text findings block to stdout, regardless of outcome.
reflect --check-id weekly-coaching-patterns --check hermitd-fitness:weekly-coaching-patternsclassifies the result from this block.
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.
- 11d ago First seen · 74 lines · 49 tokens per session scan A d00336250245
weekly-coaching-patterns is a skill published in the GitHub repository gtapps/hermitd (79 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,319 once invoked, about $0.0002 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 2026-10-02.
Other skills, from other repositories
reinforcement-learning
Reinforcement Learning best practices for Python using modern libraries (Stable-Baselines3, RLlib, Gymnasium). Use when: Implementing RL algorithms (PPO, SAC, DQN, TD3, A2C) Creating custom Gymnasium environments Training, debugging, or evaluating RL agents Setting up hyperparameter tuning for RL Deploying RL models…
cpp-reinforcement-learning
C++ Reinforcement Learning best practices using libtorch (PyTorch C++ frontend) and modern C++17/20. Use when: Implementing RL algorithms in C++ for performance-critical applications Building production RL systems with libtorch Creating replay buffers and experience storage Optimizing RL training with GPU acceleration…
research-poster
Turns a PDF abstract into a polished, fully-editable scientific conference poster (.pptx + PDF + preview) in a matched house style, with honest charts, verified citations, big readable typography, and a render-and-QA loop. Use whenever the user wants to make, build, design, or create a research poster, scientific…
open-problem
Use when the user points at a hard, unsolved, or open problem in any field — mathematics, physics, biology, ML, engineering — and wants a real attack on it. Runs a sustained multi-agent assault: establishes the state of play from primary sources, hunts for the two literatures nobody has combined, generates and kills…
especialista-em-informacao-em-saude
Especialista em Informação em Saúde. Use para dados clínicos e administrativos, sistemas de informação, qualidade do dado e inteligência de gestão em saúde. Palavras-chave: informação em saúde, dados clínicos, dados administrativos, DATASUS, sistemas de informação, inteligência de gestão.
especialista-em-gestao-de-saude
Especialista em Gestão de Saúde. Use para gestão de saúde e serviços assistenciais: indicadores de saúde, qualidade assistencial, regulação, saúde populacional e conformidade. Palavras-chave: gestão de saúde, assistencial, indicadores, qualidade, regulação, saúde populacional, LGPD/HIPAA.