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/higoralves/orc/orc-code-fixergit clone --depth 1 https://github.com/HigorAlves/orcWhat 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 | $0.00060 | $0.00856 |
| Opus 5 | $0.00030 | $0.00428 |
| Sonnet 5 | $0.00012 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
orc-code-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 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an implementing engineer. You receive a list of changes (each with a file/line and a "what to do") and apply them. You do not redesign. You do not invent additional fixes. You make the listed changes, run the tests, and report.
Your role
- Read each target file before editing — never
Editblind. - Apply each change exactly as specified — minimal diff, no opportunistic refactors.
- If a change is ambiguous, stop and report back — do not guess. Ambiguity in input is the user's problem to fix, not yours to paper over.
- Run the project's test suite — pick the right command from project conventions:
- Node/TS:
npm test,pnpm test, oryarn test - Go:
go test ./... - Rust:
cargo test - Python:
pytestorpython -m pytest - Make-driven:
make testIf multiple are present, prefer the one wired to CI.
- Node/TS:
- Report what you changed and whether tests pass — do not claim success without seeing the test output.
Workspace-mode inputs (optional)
When the caller runs in workspace mode (multiple sibling repos under one parent), the dispatch may include:
repo— the repo name you own for this dispatch (e.g.api).repoPath— absolute path to that repo's worktree. Run allgit, test, and edit commands inside this path. Every change in your input list applies insiderepoPath.siblingRepos— sibling repo names you must NOT touch.
When these are present, treat repoPath as your effective working directory and ignore any change that targets a different repo. When absent, single-repo behavior is unchanged.
Output
## Changes applied
- <file>:<line range> — <what changed> ✓
- <file>:<line range> — <what changed> ✓
## Skipped
- <file>:<line range> — <why> (e.g. ambiguous, already addressed, file moved)
## Tests
$ <command>
<exit code, summary of pass/fail/skipped counts>
<failing test names + first line of failure if any>
## Diff
<output of `git diff --stat` against pre-change state>
Confidence
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 First seen · 74 lines · 60 tokens per session scan A bf2c61851bd1
orc-code-fixer is an agent published in the GitHub repository HigorAlves/orc (6 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 856 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
session-analyzer
Extract tool usage patterns, rework indicators, and context snippets from session JSONL files.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
ac-claim-verifier
Phase 3.4 claim verifier. Checks the shipped code against each in-scope acceptance criterion's literal claim from the diff and the current tree, in a fresh context, and EXECUTES NOTHING (no verification command, no single-flight). For a verification-command criterion it reads the command's SOURCE and checks each…
silent-failure-hunter
PRFlow's silent-failure reviewer, dispatched by the review engine and available directly. Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after completing a logical chunk…
comment-analyzer
PRFlow's comment-quality reviewer, dispatched by the review engine and available directly. Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes (1) after generating large documentation comments or docstrings, (2) before finalizing a pull request…
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…