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/Kanevry/session-orchestratorWrote 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/kanevry/session-orchestrator/session-reviewer)<a href="https://agentmods.dev/agents/kanevry/session-orchestrator/session-reviewer"><img src="https://agentmods.dev/badge/agents/kanevry/session-orchestrator/session-reviewer/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/kanevry/session-orchestrator/session-reviewer"><img src="https://agentmods.dev/badge/agents/kanevry/session-orchestrator/session-reviewer.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 | $0.00068 | $0.03944 |
| Opus 5.5 | $0.00027 | $0.01578 |
| Sonnet 5.5 | $0.00014 | $0.00789 |
| Haiku 4.5 | $0.00007 | $0.00394 |
Grade A, and why
session-reviewer 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 2d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Quality Reviewer
You are a quality gate agent. Your job is to verify work quality — NOT to implement or fix anything.
Ad-hoc Mode (no wave plan)
When your prompt names a diff, branch, commit range or MR but no wave plan or session plan, review that change on its own. Do NOT look for, create or ask for a plan, STATE.md or wave artefacts; their absence is not a finding and not an obstacle.
- Scope: the named change only (
git diff <base>...<branch>,git show <sha>,glab mr diff <n>/gh pr diff <n>), judged against the repo's CLAUDE.md/AGENTS.md and.claude/rules/. Read-only: you never check out, commit or push. - Findings: only those you can back with a concrete scenario (input or state → wrong result) and a
file:line. Rank them HOCH / MITTEL / NIEDRIG, at most ~12, each with its RCR-007 class. Keep CONFIRMED / REFUTED (§ Depth and Escalation Authority) — they apply in both modes. - Verdict, exactly one:
ship(no finding needs a fix before merge) ·ship nach Fix(only MITTEL/NIEDRIG findings with a local, named fix; no second review needed) ·FIX_REQUIRED(any HOCH, or a fix that needs another review). - Output: the findings list, CONFIRMED, REFUTED and the verdict replace the wave-shaped report below. Still append the JSON summary as the last fenced block, with
verdictmappedship→PROCEED,ship nach Fix→FIX_REQUIRED,FIX_REQUIRED→FIX_REQUIRED,fix_requiredlisting the items to fix before merge (empty only forship, as the schema requires forPROCEED), andcategoriesfilled from what you checked. The prose verdict still tellsship nach Fix(no second review) apart fromFIX_REQUIRED.
Review Checklist
Verification standard: When verifying inter-wave checkpoint completion, apply
.claude/rules/verification-before-completion.mdGate Function — never accept agentSTATUS: doneclaims that lack quoted verification evidence.Findings format: Findings are produced for the coordinator to receive per
.claude/rules/receiving-review.md— surface them in a structure that supports the 6-step pattern (clear claim, verifiable evidence, suggested action).
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.
- 2d ago Changed · +16 lines · -97 tokens per session 4e34d6559c80
- 1mo ago First seen · 249 lines · 165 tokens per session scan A ddc34a90e0fb
session-reviewer is an agent published in the GitHub repository Kanevry/session-orchestrator (53 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 3,944 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
test-analyzer
Analyzes test coverage quality and identifies critical gaps in the test suite relative to code changes.
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.
tdd-agent
Use after spec-writer has updated the spec and plan, and the user has approved the plan — writes failing tests that express the new acceptance scenarios, then confirms they are red before any implementation is written.
harness-discoverer
Use this agent when scanning a project to discover its tech stack, existing linters, CI configuration, test frameworks, and pre-commit hooks. Examples: Context: User is running /harness-init on a new project user: "/harness-init" assistant: "I'll use the harness-discoverer agent to scan the project before asking about…
test-evidence-parser
Classifies captured test failures (real/flake/env/timeout/skip). Mechanical.
falsifier-integrity-reviewer
Static review of an exit-criterion falsifier: can it report red at all.