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/snapsynapse/skill-provenance/opennpx skills add snapsynapse/skill-provenance --skill opengit clone --depth 1 https://github.com/snapsynapse/skill-provenanceWrote 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/snapsynapse/skill-provenance/open)<a href="https://agentmods.dev/skills/snapsynapse/skill-provenance/open"><img src="https://agentmods.dev/badge/skills/snapsynapse/skill-provenance/open.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.00795 |
| Opus 5 | $0.00044 | $0.00398 |
| Sonnet 5 | $0.00018 | $0.00159 |
| Haiku 4.5 | $0.00009 | $0.00080 |
Grade A, and why
open 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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Provenance: Open
Verify a skill bundle when opening a session. This ensures you start from a known-good state before making any changes.
When to use
Run /skill-provenance:open at the start of any session where you'll work
on a skill bundle — a directory containing SKILL.md and optionally
MANIFEST.yaml, CHANGELOG.md, evals, scripts, and other tracked files.
Protocol
-
Read MANIFEST.yaml first. It is the single source of truth for what the bundle contains. If no manifest exists, tell the user and suggest running
/skill-provenance:bootstrapinstead. -
Verify all listed files are present. Report any files listed in the manifest but missing from disk.
-
Verify structure and hashes. Prefer the bundle's
validate.shwhen available so constrained path grammar, duplicate inventory entries, symlink components, missing or malformed hashes, and explicithash: nullopt-outs are handled consistently. Otherwise compute SHA-256 manually for every manifest-listed pinned file and report reduced assurance. -
Read CHANGELOG.md. Summarize the most recent 2-3 entries so the user knows what changed recently.
-
Check for staleness. Use hash drift, recent changelog dependency notes, internal-header conflicts,
validated_against, and deployment records. Never compare per-file revision integers numerically with bundle semver; they are separate version domains. -
Check deployment drift. If the manifest has a
deploymentssection, note any deployed copies whose version appears behind the current bundle version. Don't alarm — just surface the information. -
Resolve conflicts if found. If a file's internal version header disagrees with the manifest's version for that file, or two files claim different bundle versions:
- Present the specific discrepancy to the user.
- Show what each version claims via its
change_summary. - Default recommendation: trust the most recent
version_date. - Always ask the user for explicit confirmation. Never silently resolve a version conflict.
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.
- 4d ago First seen · 83 lines · 89 tokens per session scan A 8b80083e8c4c
open is a skill published in the GitHub repository snapsynapse/skill-provenance (7 stars, last pushed 5d ago), licensed MIT. It adds 89 tokens to every session and 795 once invoked, about $0.0004 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
architecture
Project architecture and file structure conventions for all process types. Use when: (1) Creating new files or modules, (2) Deciding where code should go, (3) Converting single-file components to directories, (4) Reviewing code for structure compliance, (5) Adding new bridges, services, agents, or workers.
testing
Testing workflow and quality standards for writing and running tests. Use when: (1) Writing new tests, (2) Adding a new feature that needs tests, (3) Modifying logic that has existing tests, (4) Before claiming a task is complete.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
deep-execution
Executes agent-enhanced council queries by spawning parallel Claude subagents that each query a provider, evaluate response quality, ask follow-up questions, and return structured insights with confidence ratings and blind spot analysis. Invoked when the --agents flag is used or when complex architectural decisions…
dividend-analysis
Comprehensive capital allocation analysis: dividends, buybacks, M&A, debt management, and FCF deployment.
position-ladder
Plan a staged position — entry ladder, share-count floor/ceiling, and the trim/re-add cycle that lowers average cost — with lot accounting, wash-sale checks, total-return honesty, and a thesis-break exit gate.