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 contextstream/mcp-server --skill agent-coachgit clone --depth 1 https://github.com/contextstream/mcp-serverWrote 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/contextstream/mcp-server/agent-coach)<a href="https://agentmods.dev/skills/contextstream/mcp-server/agent-coach"><img src="https://agentmods.dev/badge/skills/contextstream/mcp-server/agent-coach/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/contextstream/mcp-server/agent-coach"><img src="https://agentmods.dev/badge/skills/contextstream/mcp-server/agent-coach.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 | $0.00097 | $0.02002 |
| Opus 5.5 | $0.00039 | $0.00801 |
| Sonnet 5.5 | $0.00019 | $0.00400 |
| Haiku 4.5 | $0.00010 | $0.00200 |
Grade A, and why
agent-coach 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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Coach Kit
The person is teaching you a piece of work they need again and again. Each time, do the work well, make giving feedback easy, and carry what they teach you into the next job.
Words
- Workflow: the recurring work (
weekly-note). It has a goal: what good looks like every time. - Job: one occasion of the work (
weekly-note#4). It has an objective: what this one must achieve. - Version: each draft you save (
weekly-note#4/v2). - Feedback: the person's own words about one version, kept exactly as said (
weekly-note#4/f1). It is either reusable (later jobs too) or this job only. - Guidance: your reading of reusable feedback (
weekly-note/g3). The person can edit it, limit where it applies, retire it or remove it.
Everything lives in the person's ContextStream account. Three tools reach it:
workflowreads:list,get,context,compare,history,metrics,export.workflow_savesaves:create,start_job,save_output,add_feedback,record_verdict,close_joband the changes below.workflow_deletedeletes one whole workflow, only after the person confirms.
Each job
- Find the workflow with
workflowlist.- For new work, help the person turn a rough idea into a short goal: who it's for, the result they want, an example or two, and any limits.
- Show the goal you propose in one line and ask only about what's missing. Then save it with
workflow_savecreate(name,goal). - A rough goal is fine; it gets sharper as you go.
- Propose the objective.
workflowgetshows recent objectives, the guidance, what still needs attention in an open job, and any coaching preference the person set. Feedback it shows from earlier jobs is history: never apply it.- Show the objective you propose in one line, and ask only about what changed or is missing. If the person asked for quick coaching, state it in that line and go on.
- Then
workflow_savestart_job(workflow,objective). To pick up an open job, readworkflowcontextfor it.
- Use what you were given.
workflowcontextholds the goal, the active guidance, this job's own feedback, and approved examples. Each guidance item shows what the person actually said beside your earlier reading, plus any limit on where it applies.- Apply each guidance item that fits this job. If its limit says it doesn't apply here, say so.
- Approved examples show what worked. Learn from them, but don't copy them: a different result can be just as good.
- Feedback from other jobs is left out on purpose. Don't bring back one-off choices you remember from them. In a comparison, anything marked "this job only; not for later jobs" stays with its job.
- Save the draft before you show it with
workflow_savesave_output(job, andtext,urlor the attachedfile).- A revision: add
reviseswith the version it revises. - Pass the
context_etagfrom the context you wrote from. carry_notesays briefly what you kept from approvals and which feedback you applied.- Name the same items in
carried, one each:{"ref": "weekly-note/g1", "how": "applied"}. The how is kept, adapted, applied or not_applied. Items marked applied or kept stop showing as needing attention.
- A revision: add
- Show it with its version reference. In a line or two, say what changed since the last version and why, and what still needs attention.
- Record each reaction. When the person reacts to a version, record their words exactly with
workflow_saveadd_feedback(output,kindcorrection, partial_approval or direction,scopeworkflow or job,words, and yourinterpretationkept apart).- Recording the reaction is part of revising; tell them what you recorded rather than asking first whether to remember it.
- Choose the scope from what they said, and say which in one line: "Saved for later jobs too; say 'just this job' if not." Ask only when a wrong guess would matter.
- To change the scope later:
workflow_saverescope_feedback. - When they approve one part, add
excerpt. For audio or video, addtime_start_msandtime_end_ms. - When they repeat something already in the guidance, add
repeat_ofwith that guidance. That shows the coaching didn't stick.
- Revise or finish.
- When they're happy:
workflow_saveclose_job(job,used). - To compare with the last job:
workflowcompare, then ask which is better. - As soon as they say, record their verdict with their words:
workflow_saverecord_verdict(job,verdictbetter, same or worse,notewith their words). It works before or after the job is closed. - The verdict is the person's choice.
- When they're happy:
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.
- 2d ago First seen · 88 lines · 97 tokens per session scan A 1e8b3add7af8
agent-coach is a skill published in the GitHub repository contextstream/mcp-server (44 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 2,002 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 2026-10-14.
Other skills, from other repositories
skills-updater
Check and update installed Claude Code skills from multiple sources (Claude plugins and npx skills). Scans for available updates, supports batch or individual updates with intelligent local change merging, and recommends popular skills from skillsmp.com and skills.sh marketplaces. Use when users want to update skills…
ralph-wiggum
Implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code.
muse-commands
Run MUSE /resume, /save and /bye for continuous work in Codex or Claude Code, preserving the selected role, Lane, decisions and source evidence across sessions.
context-health-check
Check actual session context observations; save and reassess after compaction without forcing Bye or guessing model limits.
peon-ping-toggle
Toggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sounds during a Claude Code session. Also handles config changes like volume, pack rotation, categories — any peon-ping setting.
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".