A skill for telling Archguardian, a code-scanning tool, to ignore a specified finding pattern in future scans. A finding pattern is a recurring warning identified by a rule, message, or file scope.

Use it to dismiss a rule, optionally limit the dismissal to a message pattern or file glob, inspect existing dismissals, or remove one.

It prevents known, accepted warnings from repeatedly appearing in later scan results. Dismissals are stored in the project so they can be reviewed or removed.

How ysfAskri/archguardian configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ysfAskri/archguardian. 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/ysfAskri/archguardian/master/.claude/skills/dismiss/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ysfAskri/archguardian

Made for: Claude Code.

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/ysfaskri/archguardian/dismiss/github.svg)](https://agentmods.dev/skills/ysfaskri/archguardian/dismiss)

Your own site

<a href="https://agentmods.dev/skills/ysfaskri/archguardian/dismiss"><img src="https://agentmods.dev/badge/skills/ysfaskri/archguardian/dismiss/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/ysfaskri/archguardian/dismiss"><img src="https://agentmods.dev/badge/skills/ysfaskri/archguardian/dismiss.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 376 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	$0.00011	$0.00376
Opus 5.5	$0.00004	$0.00150
Sonnet 5.5	$0.00002	$0.00075
Haiku 4.5	$0.00001	$0.00038

Measured 1mo ago against content hash 6fc4ae164fee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dismiss 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 1mo 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.

.claude/skills/dismiss/SKILL.md · 46 lines

What it actually says

archguardian dismiss

Dismiss a finding pattern so it no longer appears in future archguardian scans.

Instructions

Run the dismiss command with the specified rule ID:
```
npx archguardian dismiss <ruleId> $ARGUMENTS
```
If the user wants to scope the dismissal, add optional flags:
- --pattern "message" — Dismiss only findings matching a specific message pattern
- --file "glob" — Dismiss only findings in files matching the glob pattern
Example:
```
npx archguardian dismiss security/xss --pattern "innerHTML assignment" --file "src/legacy/**"
```
After dismissing, show the user what was dismissed:
- The rule ID that was dismissed
- Any pattern or file scope that was applied
- How many existing findings this would suppress
Mention that dismissed findings are stored in .archguard/memory.json and can be reviewed or removed later.
If the user wants to see current dismissals:
```
cat .archguard/memory.json
```

Tips

Dismissed patterns persist across scans and are stored in .archguard/memory.json.
To undo a dismissal, the user can edit .archguard/memory.json directly or run the dismiss command again with --remove.
Prefer scoped dismissals (--pattern or --file) over blanket rule dismissals to keep coverage high.
If the finding is a one-off false positive, suggest using /suppress with an inline comment instead.

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.

1mo ago First seen · 46 lines · 11 tokens per session scan A 6fc4ae164fee

Subscribe to this mod's changes

dismiss is a skill published in the GitHub repository ysfAskri/archguardian (4 stars, last pushed 8mo ago), licensed MIT. It adds 11 tokens to every session and 376 once invoked, about $0.0000 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.

Security ai-code architecture ast cli code-quality conventions

hefestoai

Run HefestoAI before committing AI-generated code: pre-commit / CI quality gate for semantic drift, security, and reliability. Use when the user asks about Hefesto, code quality gates, semantic drift, install hooks, or validating Claude/Codex/Cursor output before commit.

artvepa80/Agents-Hefesto · 61 tokens

HefestoAI Output Analysis

Interpret HefestoAI analyze / pre-commit / CI output, suggest fixes, and draft a commit-quality summary. Use after hefesto analyze, after a Hefesto hook or CI gate, or when the user asks what Hefesto found.

artvepa80/Agents-Hefesto · 56 tokens

skill

The HefestoAI agent skill moved to skills/hefestoai/ (name: hefestoai, following the Agent Skills specification). Its reference docs (commands.md, issuetypes.md, integration.md, semanticdrift.md, reliabilitydrift.md and analysis/) moved with it.

artvepa80/Agents-Hefesto · 0 tokens

repo-onboarding

Systematically map an unfamiliar codebase before changing it — entry points, build/test loop, conventions, data flow. Use when starting work in a repo you haven't seen, or asked "how does this codebase work?".

jnMetaCode/skillet · 48 tokens

code-to-diagram

Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a…

zebbern/claude-code-guide · 74 tokens

sql-linting

Lint SQL with GoSQLX and explain its rules L001-L030 (whitespace, keyword case, comma placement, aliasing, plus safety, performance and naming rules), including which rules each entry point applies and which can be auto-fixed. Use when the user asks to lint SQL, enforce SQL style, explains a GoSQLX rule ID like L007…

ajitpratap0/GoSQLX · 90 tokens

archguardian: Skill for Claude Code