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 SkillsCatalog/registry --skill skill-manifest-generatorgit clone --depth 1 https://github.com/SkillsCatalog/registryWrote 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/skillscatalog/registry/skill-manifest-generator)<a href="https://agentmods.dev/skills/skillscatalog/registry/skill-manifest-generator"><img src="https://agentmods.dev/badge/skills/skillscatalog/registry/skill-manifest-generator/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/skillscatalog/registry/skill-manifest-generator"><img src="https://agentmods.dev/badge/skills/skillscatalog/registry/skill-manifest-generator.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 | $0.00027 | $0.00676 |
| Opus 5 | $0.00014 | $0.00338 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
skill-manifest-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
Use this skill to generate a MANIFEST.json file for any Agent Skill directory. The manifest provides:
- Integrity verification - SHA256 hashes for all files and an overall integrity hash
- File inventory - Complete listing of files with sizes and types
- External URL detection - URLs found in code that reference external resources
- Structure analysis - Folder depth, file counts, and organization
When to Use
- Before publishing a skill to a catalog
- To verify a skill hasn't been modified
- To audit external dependencies in a skill
- To validate skill structure and compliance
How to Use
Run the manifest generator on a skill directory:
Generate a manifest for the skill at /path/to/my-skill
Or to verify an existing manifest:
Verify the manifest for /path/to/my-skill
Output
The generator creates a MANIFEST.json file in the skill root containing:
{
"$schema": "https://agentskills.io/schemas/manifest.v1.json",
"manifestVersion": "1.0",
"generatedAt": "2025-01-15T10:30:00Z",
"generator": "skill-manifest-generator/1.0.0",
"skill": {
"name": "my-skill",
"version": "1.0.0"
},
"integrity": {
"algorithm": "sha256",
"hash": "a1b2c3d4..."
},
"files": [...],
"externalReferences": [...],
"structure": {...}
}
Examples
Generate a manifest:
User: Generate a manifest for the skill at ./pdf-tools
Agent: I'll generate a MANIFEST.json for the pdf-tools skill...
[Runs generate_manifest.py]
Created MANIFEST.json with:
- 12 files inventoried
- Integrity hash: sha256:abc123...
- 2 external URLs detected
- Max folder depth: 2
Verify a manifest:
User: Verify the manifest for ./pdf-tools
Agent: I'll verify the MANIFEST.json matches the current files...
[Runs generate_manifest.py --verify]
✓ All 12 files match their recorded hashes
✓ No new untracked files found
✓ Integrity hash verified
What ships with it
3 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 · 105 lines · 27 tokens per session scan A 393d26785ba7
skill-manifest-generator is a skill published in the GitHub repository SkillsCatalog/registry (1 stars, last pushed 8mo ago), licensed MIT. It adds 27 tokens to every session and 676 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
context-verifier
Know the file you're editing is the file you think it is — verify integrity before you act.
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
anti-deception
Use before responding to pressure for agreement, manufactured urgency, authority appeals, or requests to certify unsupported claims; separate evidence from persuasion and state uncertainty.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
portaljs-check-data-quality
Audit a local or remote tabular file (CSV/TSV) for common data quality issues — schema, nulls, types, duplicates. Read-only. Use when a dataset needs a quality check before publishing, or a showcase renders wrong (blank cells, garbled numbers, an unsortable date column) and the cause needs isolating.
triage-validation
Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain table, CVSS 3.1 quick reference, severity decision guide, report title formula, 60-second pre-submit checklist. Use BEFORE writing any report. One wrong answer…