Borrowing it
Nothing to install: this file belongs to savant0x/savant-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/savant0x/savant-code/main/.agents/skills/fid-gates-unfenced-parser-contract/SKILL.mdgit clone --depth 1 https://github.com/savant0x/savant-codeWrote 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/savant0x/savant-code/fid-gates-unfenced-parser-contract)<a href="https://agentmods.dev/skills/savant0x/savant-code/fid-gates-unfenced-parser-contract"><img src="https://agentmods.dev/badge/skills/savant0x/savant-code/fid-gates-unfenced-parser-contract/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/savant0x/savant-code/fid-gates-unfenced-parser-contract"><img src="https://agentmods.dev/badge/skills/savant0x/savant-code/fid-gates-unfenced-parser-contract.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 | $0.00021 | $0.00392 |
| Opus 5.5 | $0.00008 | $0.00157 |
| Sonnet 5.5 | $0.00004 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
fid-gates-unfenced-parser-contract 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- fid-gates-unfenced-parser-contract — 100% identical, 38 lines differ
What it actually says
FID Verification Gates: Unfenced Declarations Required
When to Use
When bun run fid:verify <fid> --write fails with "malformed verification
gates" / "no gates declared" on a FID whose - gate: lines visibly exist.
The gate parser
(packages/agent-runtime/src/echo/fid-verification-gates.ts) strips ALL fenced
code blocks BEFORE parsing. A fence around your gates makes them invisible, and
the surrounding prose is then reported as malformed declarations.
Procedure
Declare gates as bare unfenced lines directly under ## Verification Gates:
## Verification Gates
- gate: typecheck <workspace>
- gate: test <path-to-test-file>
No prose, no fences inside that section — any non-empty line that is not a
- gate: bullet or receipt block is an error.
Pitfalls
- Wrapping the gates in a ```markdown fence silences them rather than documenting them, and the failure reads as a parse bug rather than a fence.
- Putting a prose line inside the section is an error even when the
- gate:bullets are correct.
Verification
After authoring a FID's gates section, grep it for triple-backticks between
## Verification Gates and the next ## heading — zero matches required. Then
run bun run fid:verify <fid> --write and confirm it stamps rather than warns.
Evidence: recurred at FID-2026-0824-017 closure and again at master FID-2026-0824-013 closure (2026-08-25/26).
What ships with it
2 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.
- 1mo ago Changed · +24 lines · +21 tokens per session 5836be11bfb7
- 1mo ago First seen · 26 lines · 0 tokens per session scan A baf63153964a
fid-gates-unfenced-parser-contract is a skill published in the GitHub repository savant0x/savant-code (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 21 tokens to every session and 392 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 2026-09-04.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.