An authorized penetration-testing process that acts like an attacker against a system to find and confirm real security weaknesses. Penetration testing is a controlled attempt to break into software or infrastructure before someone else does.

Use it to test your own system, an agreed staging environment, or a practice lab before launch and during ongoing security checks. It covers authorization, investigation, scanning, exploitation, reporting, and retesting.

Security scanners and tests can report possible problems without proving they are exploitable. This process confirms which weaknesses are real, how they could be combined, and what damage they could cause.

gungnir — Skill for Claude Code by IamK77/Skill

Install

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.

Any agent

npx skills add IamK77/Skill --skill gungnir

Clone the repo

git clone --depth 1 https://github.com/IamK77/Skill

Made for: Claude Code.

Or install engineering, the plugin that ships this one along with the rest of its 10 skills.

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/iamk77/skill/gungnir/github.svg)](https://agentmods.dev/skills/iamk77/skill/gungnir)

Your own site

<a href="https://agentmods.dev/skills/iamk77/skill/gungnir"><img src="https://agentmods.dev/badge/skills/iamk77/skill/gungnir/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/iamk77/skill/gungnir"><img src="https://agentmods.dev/badge/skills/iamk77/skill/gungnir.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,097 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	$0.00035	$0.01097
Opus 5.5	$0.00014	$0.00439
Sonnet 5.5	$0.00007	$0.00219
Haiku 4.5	$0.00003	$0.00110

Measured 1mo ago against content hash 495f99344c9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gungnir 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.

skills/engineering/gungnir/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gungnir

Investigate a specifically authorised security hypothesis with minimal, reproducible evidence. Use only on an agreed target and scope; deliver a bounded finding rather than speculative accusations.

Inputs

Explicit target and authorisation; allowed techniques and impact limits; a security hypothesis; a safe reproduction environment.

Run record

Use checklist 0.5 or newer for this SOP. Reading or reloading the skill must not reset work. For a new task, run checklist init "${CLAUDE_SKILL_DIR}" --new --path "/absolute/project"; retain its returned ID as RUN. For existing work, use checklist resume "$RUN", then checklist show --run "$RUN". Outside Claude, replace the skill-directory variable with this directory’s actual path.

Commands below record work after it is done. Replace evidence placeholders with concise artifact locations and observations. Manual confirmations are not independent proof; a sensor pass covers only the command and inputs it observed. verify does not close a stage; advance checks that its required readings are fulfilled. Use report --run "$RUN" for the retained history.

Procedure

authorise

Record who authorised which target and actions. Establish stop conditions for sensitive data, service impact, or scope expansion. Read local boundaries before interacting with the target.

Record these artifacts after doing the work:

Target, authority, allowed actions, and stop conditions are recorded. checklist check authorise scope --run "$RUN" --evidence "<artifact and observation>"
The suspected trust-boundary violation is stated as a testable hypothesis. checklist check authorise hypothesis --run "$RUN" --evidence "<artifact and observation>"

When this stage is fulfilled: checklist advance authorise --run "$RUN".

reproduce

Trace the relevant code path and construct the least invasive demonstration. Record prerequisites, inputs, outputs, and counterexamples. Stop rather than escalating beyond the agreed impact.

Read the full file on GitHub · 94 lines

Files

What ships with it

11 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.

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 Changed · -64 lines · -149 tokens per session 495f99344c9e
2mo ago First seen · 158 lines · 184 tokens per session scan A 2cfe24e1980c

Subscribe to this mod's changes

gungnir is a skill published in the GitHub repository IamK77/Skill (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,097 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.

Claude Code Security agent-skills anthropic claude developer-tools skills

gungnir next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gungnirIamK77/Skill	Skill	2	1mo ago	Apache-2.0	A	35	Claude Code
agents-v2-pylingxling/awesome-skills-cn	Skill	334	1mo ago	MIT	A	39	Claude Code
analytics-productlingxling/awesome-skills-cn	Skill	334	1mo ago	MIT	A	35	Claude Code
api-security-best-practiceslingxling/awesome-skills-cn	Skill	334	1mo ago	MIT	A	29	Claude Code
antigravity-workflowslingxling/awesome-skills-cn	Skill	334	1mo ago	MIT	A	41	Claude Code
apex-skillifytonone-ai/tonone	Skill	77	4d ago	MIT	A	41	Claude Code
oci-services-expertfrankxai/claude-skills-library	Skill	47	yesterday	MIT	A	43	Claude Code

gungnir

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

gungnir

Inputs

Run record

Procedure

authorise

reproduce

What ships with it

What this file has done since we first saw it

gungnir compared with skills from other repositories