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 AyushParkara/syntra --skill request-reviewgit clone --depth 1 https://github.com/AyushParkara/syntraWrote 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/ayushparkara/syntra/request-review)<a href="https://agentmods.dev/skills/ayushparkara/syntra/request-review"><img src="https://agentmods.dev/badge/skills/ayushparkara/syntra/request-review/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/ayushparkara/syntra/request-review"><img src="https://agentmods.dev/badge/skills/ayushparkara/syntra/request-review.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 | $0.00037 | $0.00360 |
| Opus 5 | $0.00018 | $0.00180 |
| Sonnet 5 | $0.00007 | $0.00072 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
request-review 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.
What it actually says
You are packaging finished work for a reviewer (often a different model). A good hand-off makes the reviewer's job fast and the verdict trustworthy.
Method — give the reviewer exactly what it needs to judge, nothing more:
- The goal in one line (what was asked).
- The deliverable — the actual changed files / output, not a prose summary of them.
- Acceptance criteria — how to know it's correct (the tests, the expected behavior).
- Decisions made + rejected approaches — so the reviewer doesn't re-litigate settled choices or suggest a dead end you already ruled out.
- Real evidence — test output, a run log, a diff — the reviewer should weigh facts over your prose.
Rules:
- Don't hide the risky parts — point the reviewer AT them ("the auth check here is the load-bearing bit"). A review that misses the danger is worthless.
- State what you DIDN'T do / what's out of scope, so the reviewer doesn't flag absence as a defect.
- Keep it tight: the reviewer's context is precious; a crisp brief beats a dump.
Output:
GOAL: ...
CHANGED: <files / the actual output>
DONE WHEN: <acceptance criteria>
DECISIONS: ... | REJECTED: ...
EVIDENCE: <tests/logs>
REVIEW THIS HARD: <the load-bearing / risky part>
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 · 35 lines · 37 tokens per session scan A d1a013ae8cfe
request-review is a skill published in the GitHub repository AyushParkara/syntra (5 stars, last pushed 29d ago), licensed Apache-2.0. It adds 37 tokens to every session and 360 once invoked, about $0.0002 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
review-harness
Use when reviewing implementation work that ran through a /tmp Pi task harness. Checks contract drift, unsafe shortcuts, validation evidence, and status honesty.
audit
Audit phase. Parallel review: code quality + security + tests. Semantic dedup of cross-mode findings. Outputs PASS/WARN/FAIL per dimension. Validates spec coverage.
perf
Performance optimizer for loops, DB queries, rendering, and batch operations. Catches N+1 queries, missing indexes, and unnecessary re-renders.
_critic
HarnessX Critic (Tier 2.1) — adversarial review of evolved-skill proposals against trace evidence. Detects reward hacking and manifest/evidence contradictions. Out-of-band LLM counterpart to the in-loop deterministic critic in src/evolve/critic.rs.
simplify
Code simplification for high-complexity files. Targets deep nesting, copy-paste patterns, and god functions.
code-review
A review process for a pull request, which is a proposed set of code changes. It examines the changed code and its surrounding files for bugs, security problems, design issues, and lint errors.