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 agentmods add instructions/stroland02/sync/agents-mdgit clone --depth 1 https://github.com/stroland02/SyncWhat 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 | $0.06449 | $0.06449 |
| Opus 5 | $0.03224 | $0.03224 |
| Sonnet 5 | $0.01290 | $0.01290 |
| Haiku 4.5 | $0.00645 | $0.00645 |
Grade A, and why
Sync AGENTS.md scanned grade A with 1 finding 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 yesterday.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**Always pass `encoding="utf-8"` explicitly** to `read_text`, `write_text`, `open`, **and `subprocess.run(..., text=True)`**. On Windows all of these default to the locale codepage — cp1252 here — so any non-ASCII byte c How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync — working conventions
Read this before writing code. It is the shared context every agent working in this repository gets; briefs and plans layer on top of it, never against it.
What this project is
Sync watches the third-party APIs a codebase calls and opens verified pull requests when one of them breaks, drifts, or wastes money. Design: docs/superpowers/specs/2026-07-25-sync-self-maintaining-apis-design.md.
The load-bearing idea is the API Dependency Graph: static call sites joined against vendor changes and runtime telemetry. Detectors query it, and all of them emit one Finding type into one remediation pipeline. If you are adding something that does not read from or write to that graph, question whether it belongs.
Latency is a design constraint, not a later optimisation
docs/superpowers/specs/2026-07-25-sync-latency-architecture.md is binding on pipeline design. Read it before changing the shape of any pipeline, adding an agent, or introducing a stage.
The rule it exists to enforce: every agent must shorten the critical path or improve a result. An agent that does neither is latency and cost with extra steps.
One consequence binds everywhere, because breaking it fails silently: any state key written by parallel branches must declare a reducer. Without one, concurrent writes are dropped — no error, no warning, missing results.
Two more, both scoped to the remediation pipeline and both in .claude/rules/remediate-stage.md: the critical path is dominated by the customer's CI run, and locate → patch → verify is a data dependency rather than an ordering accident.
This is a data pipeline, and it obeys data-pipeline rules
docs/superpowers/specs/2026-07-27-sync-pipeline-discipline.md carries the argument and names what deliberately does not apply. Two of the six rules are purely about vendor adapters — keep VendorChange.raw, and a signature proves origin rather than correctness — and live in .claude/rules/signal-stage.md. The four that bind every session:
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.
- yesterday First seen · 299 lines · 6,449 tokens per session scan A a36006af14a2
Sync AGENTS.md is an instructions file published in the GitHub repository stroland02/Sync (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 6,449 tokens to every session, about $0.0322 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
onWatch CLAUDE.md
Claude Code instructions for onllm-dev/onWatch, covering onwatch, task, code map, objectives and operations.
cli AGENTS.md
Instructions for vibgrate/cli, covering agents.md, build, test, and check, prefer vg over grepping, determinism rules (non-negotiable) and public-only rule.
onWatch AGENTS.md
AGENTS.md instructions for onllm-dev/onWatch, a project described as: Track AI API quotas across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity in real time. Lightweight background daemon (<50MB RAM), SQLite storage, Material Design 3 dashboard. Zero telemetry.
mcp-ratchet AGENTS.md
Instructions for hexxla/mcp-ratchet, covering project instructions, your responsibilities as an agent, hexagonal architecture, core concepts and layer responsibilities & rules.
api-governance copilot-instructions.md
Copilot instructions for coderifts/api-governance: Call preflightchangeset before merge, deploy, publish, or tool registration when a contract artifact changed (OpenAPI/Swagger, GraphQL, gRPC/protobuf, AsyncAPI, MCP manifest, or agent tool schemas).
upgradelens AGENTS.md
AGENTS.md instructions for mattpicone/upgradelens: Remote MCP (streamable HTTP, no key for the anonymous free quota): https://upgradelens.mattpicone.workers.dev/mcp.