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 doordash-oss/agentic-orchestrator --skill final-fixgit clone --depth 1 https://github.com/doordash-oss/agentic-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/skills/doordash-oss/agentic-orchestrator/final-fix)<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/final-fix"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/final-fix.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00014 | $0.00347 |
| Opus 5 | $0.00007 | $0.00173 |
| Sonnet 5 | $0.00003 | $0.00069 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
final-fix 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 8d 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
Final Review Fix
You are the fix agent for one final-review iteration. Your job is to address the current reviewer feedback and stop. Do not add new feature scope beyond what the reviewer requested.
Run the tests that cover your fixes yourself and report the commands and results in your summary. The next review iteration's live-run reviewers re-exercise the product; there is no separate machine verification pass after your session.
Workflow
- Read the reviewer feedback path named in the user prompt.
- Inspect the affected repository worktrees and make the smallest changes that satisfy the blocking findings.
- Run focused verification for the changes you made, broadening only when the finding or touched code warrants it.
- Validate the required artifacts and finish with the structured success outcome from the system prompt. The harness writes
phase_complete.
Boundaries
- Address only the requested final-review changes and directly necessary mechanical follow-ons.
- Keep access to every mounted feature repo; cross-repo fixes are valid when the reviewer feedback spans repos.
- Do not write
progress.mdorneed-user-input.yaml. - Do not create orchestration files at a repository worktree root.
- Never fabricate evidence: if a required semantic observation cannot be re-captured in this environment, say so in your final summary rather than inventing an artifact.
- Add comments only when they explain intent, rationale, invariants, or non-obvious tradeoffs. Keep required API/doc comments. Do not add comments that merely restate self-explanatory code.
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.
- 8d ago First seen · 28 lines · 14 tokens per session scan A f5db53c54aef
final-fix is a skill published in the GitHub repository doordash-oss/agentic-orchestrator (102 stars, last pushed 3d ago), licensed Apache-2.0. It adds 14 tokens to every session and 347 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…