Borrowing it
Nothing to install: this file belongs to cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions/main/.claude/skills/sync-template/SKILL.mdgit clone --depth 1 https://github.com/cgfixit/AzureAI-CopilotStudio-PersonalAgent-InstructionsWrote 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/cgfixit/azureai-copilotstudio-personalagent-instructions/sync-template)<a href="https://agentmods.dev/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/sync-template"><img src="https://agentmods.dev/badge/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/sync-template/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/cgfixit/azureai-copilotstudio-personalagent-instructions/sync-template"><img src="https://agentmods.dev/badge/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/sync-template.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 | $0.00056 | $0.01414 |
| Opus 5.5 | $0.00022 | $0.00566 |
| Sonnet 5.5 | $0.00011 | $0.00283 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
sync-template 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 15d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Template — propagate a TEMPLATE.md change across the library
TEMPLATE.md is the canonical source; the examples (19 files — see the dialect table in CLAUDE.md §2) are its instantiations. When the shared contract changes, every example needs the change in its own dialect — this is the multi-hour chore behind release v1.4 ("Added o3 Reasoning Protocol to TEMPLATE.md and all examples"), systematized.
Step 1: Capture and classify the delta
git diff $(git merge-base HEAD origin/main) -- TEMPLATE.md
Classify each hunk (a change can be several):
| Class | Meaning | Propagation duty |
|---|---|---|
| NEW-SECTION | A section added to the contract (e.g. Reasoning Protocol in v1.4) | Add a domain-adapted equivalent to every example |
| RULE-CHANGE | Wording/strength of an existing rule changed | Update the corresponding passage in every example that carries it |
| PLACEHOLDER-SET | A [TOKEN] added, renamed, or removed |
See Step 4 — three extra files must move in lockstep |
| REMOVAL / WEAKENING | A rule or section removed, or safety language softened | STOP. Confirm with the owner before propagating — removals change the product's safety posture |
Step 2: The dialect map — how to insert into each file
Dialect variation is frozen (see CLAUDE.md). Propagate content, never structure:
| Dialect | Files | Insertion guidance |
|---|---|---|
| TEMPLATE-faithful | incident-response.md, legal-compliance.md, langchain-agents.md, manufacturing-iot.md |
Headings mirror TEMPLATE.md — insert in the same relative position with near-identical heading text. |
| Coder/KB family | ps1AgentCoder.md, pythonAgentCoder.md, yaragenerator.md |
Rules go in their rules sections (Forbidden Actions, Behavioral Rules, Reasoning Protocol) — never inside "Mandatory Output Templates A/B", which are the agent's output formats. #-comment header block, "Ground truth / Strong patterns / Advisory" tier names. |
| Narrative-tiered | cloud-infra.md, veeamGPT.md |
Sections are prose-heavy with renamed headings ("Sources to Use With High Authority", "Tutorial Creation Protocol") and <checkpoint> syntax instead of > ✅ **Checkpoint**:. Insert under the analogous renamed heading; keep their checkpoint syntax. |
| Numbered outlier | Network&SecurityAgent.md |
Sections are N. Title numbered 1-13. Append content within the closest existing numbered section — do not renumber 13 headings for one insertion. Tier hierarchy is a table; edit rows, not headings. |
| Sol variant | every *-5.6Sol.md |
Propagate the rule, not o3 scaffolding: Sol files have no Reasoning Protocol checklist by design. State each rule once in the matching policy section; keep the Enterprise boundary section intact. |
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.
- 15d ago Changed · +1 lines 275a0ff5398d
- 2mo ago First seen · 98 lines · 56 tokens per session scan A 52e76a165e45
sync-template is a skill published in the GitHub repository cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions (1 stars, last pushed 15d ago), licensed MIT. It adds 56 tokens to every session and 1,414 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 2026-08-31.
Other skills, from other repositories
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…
queues-jobs
Implement reliable asynchronous jobs and message consumers with explicit delivery, retry and shutdown semantics. Use when adding BullMQ or another established queue, background processing or scheduled work; enqueue success is not job completion.