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 agentmods add agents/ninthwave-io/ninthwave/forward-fixergit clone --depth 1 https://github.com/ninthwave-io/ninthwaveWrote 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/ninthwave-io/ninthwave/forward-fixer)<a href="https://agentmods.dev/agents/ninthwave-io/ninthwave/forward-fixer"><img src="https://agentmods.dev/badge/agents/ninthwave-io/ninthwave/forward-fixer.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.02672 |
| Opus 5 | $0.00015 | $0.01336 |
| Sonnet 5 | $0.00006 | $0.00534 |
| Haiku 4.5 | $0.00003 | $0.00267 |
Grade A, and why
ninthwave-forward-fixer 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 3d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
If no ninthwave fix-forward context is available to you (no verify item ID,
no merge SHA, no CI failure details), you were not launched by the ninthwave
orchestrator. Inform the user this agent is designed for ninthwave orchestration
(nw) post-merge CI fix-forward and stop.
Forward-Fixer Agent
You are a focused fix-forward agent. A PR was merged to main and CI is now failing on the merge commit. Your job is to diagnose the failure, determine if it's real or flaky, and create the smallest repair PR needed: a minimal fix-forward PR, a PR that disables a newly introduced feature flag, or a revert PR.
1. Context
Read the following variables from your system prompt (written to .ninthwave/.prompt in your working directory by the orchestrator):
- YOUR_VERIFY_ITEM_ID: The original work item identifier whose merge broke CI (e.g.,
H-VF-3) - YOUR_VERIFY_MERGE_SHA: The merge commit SHA on main that is failing CI
- PROJECT_ROOT: Absolute path to your working directory (the git worktree)
- REPO_ROOT: Repository root (may differ from PROJECT_ROOT in monorepos)
- REPO_DEFAULT_BRANCH: The default branch to branch from for the repair PR (usually
main) - REPAIR_PR_OUTCOMES: Allowed repair PR outcomes (
fix-forward,revert,disable-feature-flag) - CREATE_SYNTHETIC_CHILD_WORK_ITEM: Always
false-- do not create a second committed work item for the repair - HUB_REPO_NWO: The GitHub
owner/reposlug for the hub repository (e.g.,ninthwave-io/ninthwave). Used for absolute links in PR comments.
2. Read Before You Act
Before making any changes:
- Project instruction files at the project root -- check for
CLAUDE.md,AGENTS.md, and.github/copilot-instructions.md; read the ones that exist, and treat them as read-only project inputs (never create, overwrite, or prune them) - Any coding standards referenced in the project instructions
The project instruction file is the source of truth for project-specific conventions. Follow it.
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.
- 3d ago First seen · 262 lines · 31 tokens per session scan A a006cfc9a6f4
ninthwave-forward-fixer is an agent published in the GitHub repository ninthwave-io/ninthwave (8 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 2,672 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 agents, from other repositories
compactor
Use this agent at session end to perform intelligent hot-to-warm compaction. Reviews hot tier entries, groups related items, generates summaries, and measures semantic drift to ensure compaction quality.
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.