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 agentmods add skills/aveproject/ave/add-ave-recordnpx skills add aveproject/ave --skill add-ave-recordgit clone --depth 1 https://github.com/aveproject/aveWhat 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 | $0.00000 | $0.02505 |
| Opus 5 | $0.00000 | $0.01252 |
| Sonnet 5 | $0.00000 | $0.00501 |
| Haiku 4.5 | $0.00000 | $0.00250 |
Grade A, and why
add-ave-record 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 3d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
add-ave-record
The main workflow for this repo. Adds one new AVE record end to end.
Steps
1. Grill the vulnerability class first
Run grill-with-docs. Answer:
- What does a vulnerable component DO? (behavioral_fingerprint)
- What attack_class is this? (new or existing?)
- What is the worst-case impact? (drives AIVSS)
- Which engines can detect it? (evidence_basis_engines)
- Can a static scan see it, or does it need runtime? (detection_stage)
- Does it chain with other AVEs? (derivable_into)
2. Assign the next ave_id
Format AVE-YYYY-NNNNN. Never reuse a number. Check records/ for the highest.
3. Write the record JSON
records/AVE-YYYY-NNNNN.json. Must validate against the schema. Include the evidence fields:
- evidence_kind_default
- detection_stage
- detection_layer
- confidence_baseline
- evidence_basis_engines
- derivable_into
The researcher field, a common, real mistake, not a hypothetical
one: defaulting to the AVE maintainer's own name because it's the
name most readily at hand while drafting. Check first: does this
record trace to a real external CVE, paper, vendor disclosure, or
existing tool implementation? If yes, and it almost always is yes,
that source's own name or organization belongs in researcher, not
the person writing the AVE record. This exact mistake shipped on two
published records before being caught by an external maintainer being
credited incorrectly himself. See docs/specs/researcher-process.md's
Accountability and sourcing section for the full rule.
The four governance/framework fields — owasp_mcp, owasp_asi,
mitre_atlas, nist_ai_rmf — always include the key, never let one go
missing. These are the fields a CISO reads first; a security team
maps an AVE record onto their own reporting frameworks through these.
An absent key silently reads as "nobody checked this framework." An
empty array reads as "checked, no real fit was found." Only the second
one is an honest, defensible state.
owasp_mcp: required oncestatusisactive/deprecated(schema-enforced,minItems: 1) — needs at least one real mapping, verified against the OWASP MCP Top 10's own primary-source category text, not inferred from how a similar-sounding record in the corpus happened to tag itself.owasp_asi,mitre_atlas,nist_ai_rmf: not yet schema-required (that's a tracked v1.2.0 change, see the roadmap issue), but always write the key. Verify each against its own primary source (liveATLAS.yamlfor MITRE ATLAS, the actual NIST AI 100-1 text for NIST AI RMF, the framework's own published category list for OWASP ASI) before adding a value. Genuinely checked and found nothing that fits? Set it to[]and say so inaivss.notes— don't just leave the key out because the array would otherwise be empty. This exact mistake (a silently-missingowasp_asikey, not an empty one) shipped on AVE-2026-00078/00079/00080 and was caught reviewing that same PR — see docs/specs/researcher-process.md's Common Mistakes section.
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.
- 3d ago First seen · 210 lines · 0 tokens per session scan A e4973cc9fdac
add-ave-record is a skill published in the GitHub repository aveproject/ave (17 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,505 tokens. 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 2026-08-30.
Other skills, from other repositories
skill-inspector
Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious.
chef-assistant
Use when cooking or planning meals, troubleshooting recipes, learning culinary techniques.
creative-writing-coach
Helps users with creative writing and storytelling.
onboarding-guide
Guides new users through a friendly onboarding experience.
terraform-deployer
Deploy infrastructure using Terraform.
helpful-formatter
Formats and improves text responses for the user.