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 receive-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/receive-review)<a href="https://agentmods.dev/skills/ayushparkara/syntra/receive-review"><img src="https://agentmods.dev/badge/skills/ayushparkara/syntra/receive-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/receive-review"><img src="https://agentmods.dev/badge/skills/ayushparkara/syntra/receive-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 | $0.00038 | $0.00366 |
| Opus 5 | $0.00019 | $0.00183 |
| Sonnet 5 | $0.00008 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
receive-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 11d 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 received review feedback. Your job is to act on it correctly — not to blindly obey every comment, and not to dismiss any.
Method — triage each comment:
- Real defect? If the reviewer found a genuine bug/gap, fix it precisely — and only it. Don't rewrite surrounding code that wasn't flagged.
- Misunderstanding? If the comment is based on the reviewer missing context, don't silently "fix" it — clarify the context (and consider whether the code should make that context obvious, which is itself a fix).
- Wrong / out of scope? Push back with a reason. A reviewer is not always right; blindly applying a bad suggestion introduces bugs. State why you're not changing it.
- Style nitpick on a sound choice? Note it, apply if cheap, skip if it fights a deliberate decision.
Rules:
- Fix the SPECIFIC thing flagged; resist the urge to "improve" untouched code (that re-opens review surface and risks new bugs).
- Re-verify after fixing — the fix must pass the same criterion that failed.
- For each comment, record the disposition: fixed / clarified / declined(why).
- If feedback and the original plan conflict, surface it rather than guessing.
Output:
COMMENT: <what the reviewer said>
DISPOSITION: fixed | clarified | declined
ACTION: <what you changed, or why not> + re-verify evidence
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.
- 11d ago First seen · 34 lines · 38 tokens per session scan A a954c76641c9
receive-review is a skill published in the GitHub repository AyushParkara/syntra (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 366 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
skill-test
Verifies that the skill system is working correctly.
opencode-export
Export opencode sessions to self-contained HTML + JSON archives for sharing, review, or backup. Use when the user wants to save, archive, or share their AI coding session history.
gpt-image-gen
MUST read before generating images. Prompt-crafting guide for gpt-image-2.5 covering tool routing (native imagegeneration server tool vs the generateimage tool), model and quality selection, prompt structure, exact text rendering, reference-image editing, transparent assets, output formats, and multi-turn refinement.
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
claudexor
Use the local Claudexor control plane for harness-agnostic coding work across Claude Code, Codex, Cursor, and OpenCode. Use when a task benefits from route-aware harness and account selection, quota-aware account rotation, shared thread context, read-only planning or research, best-of-N execution, or cross-harness…