Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/akashrpatil/awesome-offensive-security-skillsnpx agentmods add skills/akashrpatil/awesome-offensive-security-skills/semgrep-custom-rule-writingWrote 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/akashrpatil/awesome-offensive-security-skills/semgrep-custom-rule-writing)<a href="https://agentmods.dev/skills/akashrpatil/awesome-offensive-security-skills/semgrep-custom-rule-writing"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/semgrep-custom-rule-writing/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/akashrpatil/awesome-offensive-security-skills/semgrep-custom-rule-writing"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/semgrep-custom-rule-writing.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 | $0.00048 | $0.01392 |
| Opus 5 | $0.00024 | $0.00696 |
| Sonnet 5 | $0.00010 | $0.00278 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
semgrep-custom-rule-writing 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 9d 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.
This is a copy
86% identical to api-enumeration-fuzzing-discovery — 188 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semgrep Custom Rule Writing
When to Use
- During a white-box penetration test or source code review when looking for bespoke vulnerabilities that generic SAST tools fail to detect.
- To codify and hunt for organization-specific anti-patterns (e.g., calling an internal API without passing the authentication context).
Prerequisites
- Authorized scope and target URLs from bug bounty program
- Burp Suite Professional (or Community) configured with browser proxy
- Familiarity with OWASP Top 10 and common web vulnerability classes
- SecLists wordlists for fuzzing and enumeration
Workflow
Phase 1: Understanding Semgrep Patterns
# Concept: Semgrep syntax rules:
- id: simple-eval-detection
pattern: eval(...)
message: "Avoid using eval() as it can lead to code injection."
languages: [javascript, python]
severity: ERROR
Phase 2: Utilizing Metavariables
# rules:
- id: python-exec-with-variable
pattern: exec($X)
message: "Using exec() on variable $X is dangerous."
languages: [python]
severity: WARNING
Phase 3: Pattern-Inside and Pattern-Not (Contextual Matching)
# rules:
- id: missing-auth-check-flask
patterns:
- pattern-inside: |
@app.route(...)
def $FUNC(...):
...
- pattern: return $RENDER(...)
- pattern-not-inside: |
@login_required
def $FUNC(...):
...
- pattern-not-inside: |
if current_user.is_authenticated:
...
message: "Flask route missing @login_required or explicit authentication check."
languages: [python]
severity: ERROR
Phase 4: Testing Rules via Semgrep CLI
# # semgrep --config custom-rules.yml src/
Decision Point 🔀
flowchart TD
A[Identify Pattern ] --> B{Write Rule ]}
B -->|Yes| C[Test Rule ]
B -->|No| D[Refine Scope ]
C --> E[Execute Scan ]
🔵 Blue Team Detection & Defense
- CI/CD Integration Pipeline Validation: Centralized Rule Repositories: Developer Education: Key Concepts | Concept | Description | |---------|-------------|
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 161 lines · 48 tokens per session scan A 4509d90dddd9
semgrep-custom-rule-writing is a skill published in the GitHub repository akashrpatil/awesome-offensive-security-skills (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,392 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to api-enumeration-fuzzing-discovery, differing in 188 lines, and is treated as a copy.
Other skills, from other repositories
implementing-semgrep-for-custom-sast-rules
Write custom Semgrep SAST rules in YAML to detect application-specific vulnerabilities, enforce coding standards, and integrate into CI/CD pipelines.
source-code-review
Security-focused source code review. Identifies hardcoded credentials, injection sinks, authentication weaknesses, and framework-specific vulnerabilities. Use when application source code is available for review.
implementing-semgrep-for-custom-sast-rules
Write custom Semgrep SAST rules in YAML to detect application-specific vulnerabilities, enforce coding standards, and integrate into CI/CD pipelines.
Mixed-Language Monorepos
This skill should be used when the user is auditing a "polyglot monorepo", "multi-language codebase", "microservices with different languages", "Go + Python + TypeScript", or any codebase with services written in different programming languages. Provides strategies for cross-service security analysis and unified…
review-pr
Diff-aware PR security review with verified findings and PR comment payload.
sast-semgrep
Static application security testing (SAST) using Semgrep for vulnerability detection, security code review, and secure coding guidance with OWASP and CWE framework mapping. Use when: (1) Scanning code for security vulnerabilities across multiple languages, (2) Performing security code reviews with pattern-based…