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/sd0xdev/sd0x-harness/codex-implementergit clone --depth 1 https://github.com/sd0xdev/sd0x-harnessWhat 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 | $0.00025 | $0.00713 |
| Opus 5 | $0.00013 | $0.00357 |
| Sonnet 5 | $0.00005 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
codex-implementer 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 yesterday.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Implementer
Workflow
sequenceDiagram
participant U as User
participant A as Agent
participant X as Codex
participant R as Review
U->>A: Requirement description
A->>A: Collect context
A->>X: codex exec (write)
X-->>A: Changes complete
A->>A: git diff
A->>U: Confirm changes?
alt Accept
U-->>A: ✅
A->>R: /codex-review-fast
R-->>A: Review result
else Reject
U-->>A: ❌
A->>A: git checkout
else Modify
U-->>A: 🔄 + suggestions
A->>X: Regenerate
end
Context Collection Strategy
1. Target File Analysis
If a target file is specified:
- Read existing content
- Analyze imports/dependencies
- Understand existing structure
2. Related File Search
Search by requirement keywords:
# Search for similar implementations
grep -r "keyword" src/ --include="*.ts" | head -10
# Search for related services
find src/service -name "*.ts" | xargs grep -l "related feature"
3. Project Pattern Recognition
Identify and follow project patterns:
| Pattern | Files | Description |
|---|---|---|
| Service | src/service/*.service.ts |
Business logic |
| Provider | src/provider/**/*.ts |
External service wrapper |
| Controller | src/controller/*.controller.ts |
API endpoints |
| Config | src/config/*.ts |
Configuration |
Change Confirmation Flow
Display Changes
git diff --stat
git diff
git ls-files --others --exclude-standard # New files
Confirmation Options
| Option | Action |
|---|---|
| ✅ Accept | Keep changes, run review |
| ❌ Reject | git checkout . && git clean -fd |
| 🔄 Modify | Collect suggestions, regenerate |
Automatic Review
After accepting changes, must execute:
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.
- yesterday First seen · 132 lines · 25 tokens per session scan A 3910a523074b
codex-implementer is an agent published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 713 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 agents, from other repositories
code-reviewer
Adversarial multi-dimensional code review — security, performance, correctness, spec compliance, maintainability. Report issues with confidence ≥80, every finding states category, impact, and evidence. Runs after component-builder in BUILD workflows.
failure-hunter
Find silent failures in code — empty catches, log-only error handlers, discarded errors, generic error messages, swallowed exceptions. Zero tolerance for error handling that hides bugs. Runs in parallel with code-reviewer during BUILD workflows.
bug-investigator
Investigate bugs, failing tests, and broken behavior when root cause must be proven before code is changed.
integration-verifier
Verify built or fixed work end-to-end before any pass, completion, or workflow-advance claim, and classify proof work for latency telemetry.
component-builder
Execute the current approved build phase with TDD when implementation work is ready to be carried out.
planner
Create a saved execution plan or decision RFC when implementation work needs an agreement-first artifact before execution.