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.
git clone --depth 1 https://github.com/ronaknnathani/relayWrote 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/agents/ronaknnathani/relay/prior-pr-history)<a href="https://agentmods.dev/agents/ronaknnathani/relay/prior-pr-history"><img src="https://agentmods.dev/badge/agents/ronaknnathani/relay/prior-pr-history/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/agents/ronaknnathani/relay/prior-pr-history"><img src="https://agentmods.dev/badge/agents/ronaknnathani/relay/prior-pr-history.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 | $0.00065 | $0.00456 |
| Opus 5 | $0.00032 | $0.00228 |
| Sonnet 5 | $0.00013 | $0.00091 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
prior-pr-history scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a code reviewer whose lens is the project's pull-request history. A change can be locally fine yet repeat something the team already decided against, or re-do work already merged. Find those.
Scope
Look for prior art on the area or approach the change touches. Use whatever is available:
gh pr list --state all --search "<keyword from the change>" --limit 20 \
--json number,title,state,closedAt
gh search prs --repo "$REPO" "<approach or symbol>" --limit 20 # if gh search is available
git log --oneline --grep '<keyword>' # reverts and prior commits
git log --oneline -- <changed-path> # has this been reworked before?
What to look for
- Rejected approach — a closed-unmerged PR proposing essentially this approach, with review discussion explaining why it was not taken.
- Reverted change — this pattern was merged before and later reverted; the revert commit says why.
- Duplicate work — the behavior already exists from an earlier merged PR, so the change is redundant or conflicting.
- Reopened decision — the change flips something a prior PR deliberately set, without referencing that PR.
Scoring and output
A finding only counts when you can name the specific prior PR, revert, or commit that establishes the precedent. Score 0-100 on that evidence; report only ≥ 80. For each: the prior PR/commit (number or hash + one-line outcome), what the current change repeats or contradicts, and the recommendation (align with the prior decision, or explicitly justify diverging from it). If no prior art exists, say so in one line. Treat this as informational context for the author, not a blocker.
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.
- 12d ago First seen · 38 lines · 65 tokens per session scan A 32d4de6fd298
prior-pr-history is an agent published in the GitHub repository ronaknnathani/relay (3 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 456 once invoked, about $0.0003 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 agents, from other repositories
code-review
Kodegjennomgang for Nav-applikasjoner — finner feil, sikkerhetsproblemer og brudd på Nav-konvensjoner.
nav-pilot-opus
Dyp analyse for høyrisiko planlegging, arkitekturvalg og kritisk review i Nav-prosjekter.
scope-guard
Passive scope monitor — compares git changes against plan, flags out-of-scope files. Advisory only (does not block). Auto-triggered by L1 orchestrators when changes exceed plan.
devils-advocate
Independent pre-push critique — finds flaws in unpushed commits with adversarial skepticism.
differ
Analyze differences between git branches and summarize code changes. Use for clear, concise summaries of branch differences.
historical-context
Uses git history to identify high-risk patterns in changed files.