docs: Add FAQ section for common questions#97
Open
meichuanyi wants to merge 1 commit into
Open
Conversation
|
Note
|
| Layer / File(s) | Summary |
|---|---|
FAQ section content README.md |
New FAQ section with subsections answering what AgentShield detects, getting started guidance (Quick Start, global install, --fix option), output format options, Opus Pipeline and MiniClaw features, licensing details, contribution guidelines, and links to help resources. |
Estimated code review effort
🎯 1 (Trivial) | ⏱️ ~3 minutes
🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
| Check name | Status | Explanation |
|---|---|---|
| Description Check | ✅ Passed | Check skipped - CodeRabbit’s high-level summary is enabled. |
| Title check | ✅ Passed | The title clearly and concisely describes the main change: adding a FAQ section to documentation. It is directly related to the file modification shown in the summary. |
| Docstring Coverage | ✅ Passed | No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. |
| Linked Issues check | ✅ Passed | Check skipped because no linked issues were found for this pull request. |
| Out of Scope Changes check | ✅ Passed | Check skipped because no linked issues were found for this pull request. |
✏️ Tip: You can configure your own custom pre-merge checks in the settings.
✨ Finishing Touches
🧪 Generate unit tests (beta)
- Create PR with unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.
Comment @coderabbitai help to get the list of available commands and usage tips.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@README.md`:
- Around line 915-924: Update the Opus Pipeline section so agent names and
descriptions match the main documentation: replace "Analyzer Agent, Adversarial
Agent, Reviewer Agent" with "Red Team (Attacker), Blue Team (Defender), Auditor"
and ensure each description text mirrors the detailed explanations from the main
docs; also add a blank line immediately before the usage code block containing
the command agentshield scan --opus --stream so the block renders correctly.
- Around line 887-903: The fenced code blocks in README.md lack surrounding
blank lines; update the three blocks that show the Quick Start, Install
globally, and Auto-fix examples so there is an empty line before the opening
```bash and an empty line after the closing ``` for each block (the sections
containing "npx ecc-agentshield scan", "npm install -g ecc-agentshield /
agentshield scan", and "agentshield scan --fix") to follow Markdown best
practices and ensure consistent rendering.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: f5542a60-ba05-46fe-84dd-031731dd9c07
📒 Files selected for processing (1)
README.md
Comment on lines
+887
to
+903
| ### How to get started? | ||
|
|
||
| **Quick Start (no install):** | ||
| ```bash | ||
| npx ecc-agentshield scan | ||
| ``` | ||
|
|
||
| **Install globally:** | ||
| ```bash | ||
| npm install -g ecc-agentshield | ||
| agentshield scan | ||
| ``` | ||
|
|
||
| **Auto-fix safe issues:** | ||
| ```bash | ||
| agentshield scan --fix | ||
| ``` |
There was a problem hiding this comment.
Add blank lines around fenced code blocks.
Markdown best practices require blank lines before and after fenced code blocks to ensure proper rendering across all Markdown parsers.
📝 Proposed fix for formatting
### How to get started?
+
**Quick Start (no install):**
```bash
npx ecc-agentshield scanInstall globally:
npm install -g ecc-agentshield
agentshield scanAuto-fix safe issues:
agentshield scan --fix</details>
<!-- suggestion_start -->
<details>
<summary>📝 Committable suggestion</summary>
> ‼️ **IMPORTANT**
> Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
```suggestion
### How to get started?
**Quick Start (no install):**
🧰 Tools
🪛 markdownlint-cli2 (0.22.1)
[warning] 890-890: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
[warning] 895-895: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
[warning] 901-901: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@README.md` around lines 887 - 903, The fenced code blocks in README.md lack
surrounding blank lines; update the three blocks that show the Quick Start,
Install globally, and Auto-fix examples so there is an empty line before the
opening ```bash and an empty line after the closing ``` for each block (the
sections containing "npx ecc-agentshield scan", "npm install -g ecc-agentshield
/ agentshield scan", and "agentshield scan --fix") to follow Markdown best
practices and ensure consistent rendering.
Comment on lines
+915
to
+924
|
|
||
| The Opus Pipeline is a **three-agent adversarial analysis** using Anthropic's Opus 4.6 model: | ||
| 1. **Analyzer Agent** — Deep analysis of findings | ||
| 2. **Adversarial Agent** — Attack simulation and impact assessment | ||
| 3. **Reviewer Agent** — Final recommendations and mitigation strategies | ||
|
|
||
| **Usage:** | ||
| ```bash | ||
| agentshield scan --opus --stream | ||
| ``` |
There was a problem hiding this comment.
Agent names and descriptions inconsistent with main documentation.
The FAQ describes the Opus Pipeline agents differently from the main documentation:
- FAQ (lines 917-919): Analyzer Agent, Adversarial Agent, Reviewer Agent
- Main docs (lines 370-372): Red Team (Attacker), Blue Team (Defender), Auditor
The agent descriptions also don't match the detailed explanations in the main documentation. This inconsistency could confuse users.
🔄 Proposed fix to align with main documentation
The Opus Pipeline is a **three-agent adversarial analysis** using Anthropic's Opus 4.6 model:
-1. **Analyzer Agent** — Deep analysis of findings
-2. **Adversarial Agent** — Attack simulation and impact assessment
-3. **Reviewer Agent** — Final recommendations and mitigation strategies
+1. **Red Team (Attacker)** — Finds exploitable attack vectors and multi-step chains
+2. **Blue Team (Defender)** — Evaluates existing protections and recommends hardening
+3. **Auditor** — Synthesizes both perspectives into a prioritized risk assessment
**Usage:**
```bash
agentshield scan --opus --stream
Additionally, add a blank line before the code block:
```diff
**Usage:**
+
```bash
agentshield scan --opus --stream
</details>
<!-- suggestion_start -->
<details>
<summary>📝 Committable suggestion</summary>
> ‼️ **IMPORTANT**
> Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
```suggestion
The Opus Pipeline is a **three-agent adversarial analysis** using Anthropic's Opus 4.6 model:
1. **Red Team (Attacker)** — Finds exploitable attack vectors and multi-step chains
2. **Blue Team (Defender)** — Evaluates existing protections and recommends hardening
3. **Auditor** — Synthesizes both perspectives into a prioritized risk assessment
**Usage:**
🧰 Tools
🪛 markdownlint-cli2 (0.22.1)
[warning] 922-922: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@README.md` around lines 915 - 924, Update the Opus Pipeline section so agent
names and descriptions match the main documentation: replace "Analyzer Agent,
Adversarial Agent, Reviewer Agent" with "Red Team (Attacker), Blue Team
(Defender), Auditor" and ensure each description text mirrors the detailed
explanations from the main docs; also add a blank line immediately before the
usage code block containing the command agentshield scan --opus --stream so the
block renders correctly.
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
There was a problem hiding this comment.
1 issue found across 1 file
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="README.md">
<violation number="1" location="README.md:917">
P2: The agent names here (Analyzer Agent, Adversarial Agent, Reviewer Agent) are inconsistent with the main documentation section which refers to them as Red Team (Attacker), Blue Team (Defender), and Auditor. Align these names and descriptions to avoid confusing users.</violation>
</file>
Reply with feedback, questions, or to request a fix.
Re-trigger cubic
Comment on lines
+917
to
+919
| 1. **Analyzer Agent** — Deep analysis of findings | ||
| 2. **Adversarial Agent** — Attack simulation and impact assessment | ||
| 3. **Reviewer Agent** — Final recommendations and mitigation strategies |
There was a problem hiding this comment.
P2: The agent names here (Analyzer Agent, Adversarial Agent, Reviewer Agent) are inconsistent with the main documentation section which refers to them as Red Team (Attacker), Blue Team (Defender), and Auditor. Align these names and descriptions to avoid confusing users.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At README.md, line 917:
<comment>The agent names here (Analyzer Agent, Adversarial Agent, Reviewer Agent) are inconsistent with the main documentation section which refers to them as Red Team (Attacker), Blue Team (Defender), and Auditor. Align these names and descriptions to avoid confusing users.</comment>
<file context>
@@ -858,3 +858,94 @@ MIT
+### What is the Opus Pipeline?
+
+The Opus Pipeline is a **three-agent adversarial analysis** using Anthropic's Opus 4.6 model:
+1. **Analyzer Agent** — Deep analysis of findings
+2. **Adversarial Agent** — Attack simulation and impact assessment
+3. **Reviewer Agent** — Final recommendations and mitigation strategies
</file context>
Suggested change
| 1. **Analyzer Agent** — Deep analysis of findings | |
| 2. **Adversarial Agent** — Attack simulation and impact assessment | |
| 3. **Reviewer Agent** — Final recommendations and mitigation strategies | |
| 1. **Red Team (Attacker)** — Finds exploitable attack vectors and multi-step chains | |
| 2. **Blue Team (Defender)** — Evaluates existing protections and recommends hardening | |
| 3. **Auditor** — Synthesizes both perspectives into a prioritized risk assessment |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Changes
Checklist
Summary by cubic
Adds an FAQ to the README with quick-start commands, feature overviews, and help links to improve onboarding and answer common setup questions. Documentation-only change; no code updates.
ecc-agentshield, including--fixand--opususage.Written for commit 09e60f0. Summary will update on new commits.
Summary by CodeRabbit