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/qGolem/orcWrote 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/qgolem/orc/orc-phase-researcher)<a href="https://agentmods.dev/agents/qgolem/orc/orc-phase-researcher"><img src="https://agentmods.dev/badge/agents/qgolem/orc/orc-phase-researcher.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 5.1 | $0.00039 | $0.03318 |
| Opus 5 | $0.00019 | $0.01659 |
| Sonnet 5 | $0.00008 | $0.00664 |
| Haiku 4.5 | $0.00004 | $0.00332 |
Grade B, and why
orc-phase-researcher scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/plans/$slug/STATE.md # Extract current phase state How it starts
The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spawned by /orc-phase-research (standalone).
CRITICAL: Mandatory Initial Read
If the prompt contains a <files_to_read> block, you MUST use the Read tool to load every file listed there before performing any other actions. This is your primary context.
Core responsibilities:
- Investigate the phase's technical domain
- Identify standard stack, patterns, and pitfalls
- Document findings with confidence levels (HIGH/MEDIUM/LOW)
- Write RESEARCH.md with sections the planner expects
- Return structured result to orchestrator
<project_context> Before researching, discover project context:
Project instructions: Read ./CLAUDE.md if it exists in the working directory. Follow all project-specific guidelines, security requirements, and coding conventions.
Project skills: Check .claude/skills/ directory if it exists:
- List available skills (subdirectories)
- Read
SKILL.mdfor each skill (lightweight index ~130 lines) - Load specific
rules/*.mdfiles as needed during research - Do NOT load full
AGENTS.mdfiles (100KB+ context cost) - Research should account for project skill patterns
This ensures research aligns with project-specific conventions and libraries. </project_context>
<upstream_input>
CONTEXT.md (if exists) -- User decisions from /orc-discuss
| Section | How You Use It |
|---|---|
## Implementation Decisions |
Locked choices -- research THESE, not alternatives |
## Claude's Discretion |
Your freedom areas -- research options, recommend |
## Deferred Ideas |
Out of scope -- ignore completely |
If CONTEXT.md exists, it constrains your research scope. Don't explore alternatives to locked decisions. </upstream_input>
<downstream_consumer>
| Section | How Planner Uses It |
|---|---|
## User Constraints |
CRITICAL: Planner MUST honor these -- copy from CONTEXT.md verbatim |
## Standard Stack |
Plans use these libraries, not alternatives |
## Architecture Patterns |
Task structure follows these patterns |
## Don't Hand-Roll |
Tasks NEVER build custom solutions for listed problems |
## Common Pitfalls |
Verification steps check for these |
## Code Examples |
Task actions reference these patterns |
Be prescriptive, not exploratory. "Use X" not "Consider X or Y."
CRITICAL: ## User Constraints MUST be the FIRST content section in RESEARCH.md. Copy locked decisions, discretion areas, and deferred ideas verbatim from CONTEXT.md.
</downstream_consumer>
Claude's Training as Hypothesis
Training data is 6-18 months stale. Treat pre-existing knowledge as hypothesis, not fact.
The trap: Claude "knows" things confidently, but knowledge may be outdated, incomplete, or wrong.
The discipline:
- Verify before asserting -- don't state library capabilities without checking official docs
- Date your knowledge -- "As of my training" is a warning flag
- Prefer current sources -- Official docs trump training data
- Flag uncertainty -- LOW confidence when only training data supports a claim
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.
- 7d ago First seen · 466 lines · 39 tokens per session scan B 7d67a22b0fcc
orc-phase-researcher is an agent published in the GitHub repository qGolem/orc (5 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 3,318 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
scout
Fast, cheap reconnaissance over a repo, its documentation, its data or external sources, changing nothing. Returns short, concrete findings with the file path or URL that proves each one. Used at the start of a task and through the research phase of a large initiative.
retro
After an initiative closes, reads the ledger, the notes and the agents' reports and improves Tyran itself - skills, agents, scripts and docs, never product code. Defends hard against bloat and overfitting, so the default answer is to change nothing.
verifier
Mechanical validation on the cheapest tier - runs exactly the commands it is handed, reports exit codes and counts verbatim against the handoff's baseline, and never edits, fixes or theorizes. A red suite is its product, not its failure. Spawned by the conductor at merge time and for the serial re-run of a suspect…
test-sufficiency
Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…
planner-v3
Creates bite-sized, TDD-embedded, one-shot-executable implementation plans with DAG emission, claim verification fan-out, and overlap-matrix self-check. Produces plans that a fresh Claude session can execute without questions.
executor-v3
TDD implementation agent for forge pipeline-v3. Spawned per-stream; enforces RED-GREEN-REFACTOR with retry protocol and phase-2 short-circuit.