What is agent-integration?

A set of instructions for safely installing, removing, and configuring RepoGrammar integrations with coding agents. It covers agent configuration, backups, validation, reversible receipts, self-tests, and controlled instruction-file edits.

Use it when adding or removing MCP connections, running installation or uninstall commands, checking integrations, repairing configuration, or editing agent instruction files with explicit consent.

It reduces the risk of corrupting agent configuration or making changes that are hard to undo. It also clarifies which commands own project state and which files must not be changed automatically.

How SioYooo/RepoGrammar configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to SioYooo/RepoGrammar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/SioYooo/RepoGrammar/main/.agents/skills/agent-integration/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/SioYooo/RepoGrammar

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sioyooo/repogrammar/agent-integration/github.svg)](https://agentmods.dev/skills/sioyooo/repogrammar/agent-integration)

Your own site

<a href="https://agentmods.dev/skills/sioyooo/repogrammar/agent-integration"><img src="https://agentmods.dev/badge/skills/sioyooo/repogrammar/agent-integration/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sioyooo/repogrammar/agent-integration"><img src="https://agentmods.dev/badge/skills/sioyooo/repogrammar/agent-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 413 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00025	$0.00413
Opus 5.5	$0.00010	$0.00165
Sonnet 5.5	$0.00005	$0.00083
Haiku 4.5	$0.00003	$0.00041

Measured 2mo ago against content hash 800ed99bbfb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-integration 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 2mo 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.

.agents/skills/agent-integration/SKILL.md · 66 lines

What it actually says

Purpose

Keep machine-level agent integration safe, reversible, and scoped.

Trigger conditions

Use when editing repogrammar install, repogrammar uninstall, MCP configuration writes, installation receipts, or agent instruction-file edits.

Required reading

docs/specifications/installation.md
docs/decisions/ADR-0007-safe-install-progress-telemetry.md
docs/specifications/mcp-api.md

Preconditions

Identify target agent and scope.
Confirm dry-run and print-config behavior are available.
Confirm consuming repositories are not forced to mirror RepoGrammar's own root guide policy.

Step-by-step procedure

Detect supported agents.
Prefer native agent configuration commands where available.
Preserve unknown config fields.
Refuse malformed config by default.
Back up before approved repair.
Write atomically and reparse after writing.
Store a reversible receipt.
Validate MCP integration with a self-test.
Only modify instruction files with marker fences and explicit consent.
Never create or delete repository-local .repogrammar/ indexes from install or uninstall; project state belongs to init and uninit.

Required verification

Run installer parsing tests, self-test validation tests when implemented, and the full repository verification suite.

Documentation updates

Update docs/specifications/installation.md, README, CHANGELOG, and MCP docs as needed.

Commit requirements

Never commit machine-local receipts or generated user config. Commit tests and docs with installer behavior.

Completion report

Report target agents, scopes, dry-run behavior, receipt behavior, and any configuration that remains unsupported.

Failure and rollback handling

If config is malformed or unknown ownership cannot be proven, do not write. Report the blocker and leave user configuration untouched.

Changes

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.

2mo ago First seen · 66 lines · 25 tokens per session scan A 800ed99bbfb8

Subscribe to this mod's changes

agent-integration is a skill published in the GitHub repository SioYooo/RepoGrammar (0 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 413 once invoked, about $0.0001 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.

Rust Testing code-analysis coding-agents developer-tools local-first mcp

architecture-audit

Systematic architecture audit and refactoring methodology for Rust + TypeScript codebases. Use when performing refactoring, cleanup, unification, code review, dead code removal, module reorganization, or tech debt elimination. Ensures no naming confusion, semantic overloading, hidden defaults, duplicate logic, or…

org2AI/ORG2 · 70 tokens

presentations

Build PowerPoint (PPTX) decks — pptxgenjs when Node is present, python-pptx when not; edit existing decks in place via OOXML — with visual QA before delivery.

brightwave-inc/tidebreak · 44 tokens

e2e-testing

ORGII keeps two separate E2E surfaces. Do not use one as proof for the other.

org2AI/ORG2 · 0 tokens

dual-instance-verification

Two-device verification protocol for ORG2 cloud sync and session sharing. Use before declaring any sharing/sync/collab feature or fix "verified": share/unshare, push/retract, fork/import, comments, member-floor, replay, continuation, or anything touching Org2CloudSyncEngine, collab engines, or the session channel…