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.
npx skills add magnus919/agent-skills --skill neckbeardgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/neckbeard)<a href="https://agentmods.dev/skills/magnus919/agent-skills/neckbeard"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/neckbeard/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/magnus919/agent-skills/neckbeard"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/neckbeard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00184 | $0.03174 |
| Opus 5 | $0.00092 | $0.01587 |
| Sonnet 5 | $0.00037 | $0.00635 |
| Haiku 4.5 | $0.00018 | $0.00317 |
Grade A, and why
neckbeard 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
neckbeard
A disciplined operating model for software delivery. It does not perform a character. It makes an agent do six things reliably: frame the change, discover the real system before designing, pick the smallest safe intervention, execute by stage, record evidence, and stop or escalate when the evidence runs out.
The name is a joke about the "10x developer in a Markdown file" trope. The substance is the opposite of that trope: effectiveness here is earned by observable outcomes and scoped claims, never asserted by a persona.
When to load this
Load neckbeard when a request is a non-trivial software change — a bug to diagnose, a feature to build, a refactor, a review, a release to verify — and you need a bounded, stage-aware way to carry it to a defensible "done."
When not to use
Do not load it for:
- A single factual question or lookup (answer directly).
- A one-line edit whose contract is already fully specified (just do it, but still verify at the boundary).
- A task already owned end-to-end by a more specific skill (route there; see references/routing-table.md).
Core loop
Every run moves through the same spine. Each stage has entry conditions, required evidence, exit conditions, and escalation rules detailed in references/stages.md.
-
Frame the change contract. State the user-visible problem, constraints, system boundary, risks, and explicit non-goals. Distinguish authority to explore from authority to modify, publish, deploy, or merge. Stop early if no change is justified, and keep the evidence for that decision. Template: templates/change-contract.md.
-
Discover before designing. Inspect the actual repository, contribution guidance, architecture, callers, tests, config, and recent changes before proposing a fix. Prefer primary evidence (code, tests, runtime output, project docs) over plausible architecture narratives. Make unverified assumptions and missing access explicit.
What ships with it
40 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.
- eval/baseline-protocol.md 4.2 KB
- eval/fixtures/adversarial/needs-a-dependency/task.yaml 1.3 KB
- eval/fixtures/adversarial/process-not-code/task.yaml 1.4 KB
- eval/fixtures/bug-diagnosis/csv-export-off-by-one/task.yaml 1.0 KB
- eval/fixtures/feature-change/add-csv-encoding-option/task.yaml 860 B
- eval/fixtures/no-change-needed/phantom-memory-leak/task.yaml 1.2 KB
- eval/fixtures/refactor/extract-csv-writer/task.yaml 821 B
- eval/fixtures/regression-prevention/guard-empty-export/task.yaml 928 B
- eval/fixtures/regression-prevention/test-hardening-mutant-guard/task.yaml 1.4 KB
- eval/fixtures/release-verification/verify-release-artifact/task.yaml 1.1 KB
- eval/fixtures/review-finding/review-sql-interpolation/task.yaml 1010 B
- eval/fixtures/spec-ambiguity/ambiguous-retention-requirement/task.yaml 1005 B
- eval/fixtures/trajectories/full-change-request/task.yaml 1.5 KB
- eval/fixtures/trajectories/lightweight-test-hardening/task.yaml 2.1 KB
- eval/fixtures/trajectories/reduced-docs-only/task.yaml 1.8 KB
- eval/rubric.md 3.5 KB
- eval/run_eval.py 16 KB runs code
- eval/task-schema.md 5.9 KB
- evals/evals.json 34 KB
- manifest.yaml 8.2 KB
- README.md 6.5 KB
- references/delivery-packet.md 18 KB
- references/evaluation.md 6.3 KB
- references/evidence-ledger.md 2.7 KB
- references/journey.md 29 KB
- references/lifecycle.md 21 KB
- references/lightweight-test-hardening.md 3.3 KB
- references/position-assessment.md 12 KB
- references/risk-authority-gates.md 5.1 KB
- references/routing-table.md 16 KB
- references/stages.md 21 KB
- references/tracker-discovery.md 6.2 KB
- research/journey-sdlc-validation-brief.md 29 KB
- research/journey-sdlc-validation-log.md 8.9 KB
- templates/change-contract.md 4.3 KB
- templates/decision-record.md 845 B
- templates/delivery-packet.md 12 KB
- templates/eval-report.md 2.1 KB
- templates/evidence-ledger.md 2.9 KB
- templates/verification-plan.md 1.1 KB
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.
- 7d ago First seen · 238 lines · 184 tokens per session scan A 3e6bd104c029
neckbeard is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 184 tokens to every session and 3,174 once invoked, about $0.0009 per session on Opus 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 2026-09-03.
Other skills, from other repositories
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
stall
Show CocoStall loop and no-progress detection status.
stall-reset
Reset CocoStall counters after an operator-approved recovery.
stall-status
Report current CocoStall no-progress and loop state.
stall-thresholds
Show or update CocoStall thresholds.
taiyi-health
A codebase health review process that samples recently changed production modules and test files, then checks for issues such as duplication, unused code, and unused dependencies.