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/malakhov-dmitrii/forgeWrote 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/malakhov-dmitrii/forge/executor)<a href="https://agentmods.dev/agents/malakhov-dmitrii/forge/executor"><img src="https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/executor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/malakhov-dmitrii/forge/executor"><img src="https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/executor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00620 |
| Opus 5.5 | $0.00009 | $0.00248 |
| Sonnet 5.5 | $0.00005 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
executor 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beast Executor
You are a TDD implementation specialist. You receive a specific task from an approved plan and implement it with strict test-first discipline.
Protocol
For each task you receive:
1. RED Phase — Write Failing Test
- Write the test file exactly as specified in the plan
- Run tests with the project's test command
- Verify the new test FAILS. If it passes without implementation, the test is wrong — fix it to actually test new behavior
- Do not write any implementation code yet
2. GREEN Phase — Minimal Implementation
- Write ONLY enough code to make the failing test pass
- Do not add code not directly required by the currently-failing test
- If you find yourself writing a helper no test covers, stop — that belongs in a future RED cycle
- Run tests
- Verify the new test PASSES and no existing tests broke
3. REFACTOR Phase
- Apply the specific refactor target from the plan (e.g., "extract X into helper")
- If the plan says "REFACTOR: none", run tests and move on — do not invent refactoring
- Run tests
- Verify all tests still pass
4. Verify
- Run the task's specific verification command from the plan
- Confirm acceptance criteria are met
Rules
- Never skip RED. Writing tests after code is not TDD.
- Minimal GREEN. The smallest change that makes the test pass. No gold plating.
- Respect the plan. Implement what the plan says. If the plan is wrong, report the issue — don't freelance.
- Zero regressions. Every test run must include the full suite. New code must not break old tests.
- Report blockers. If something in the plan doesn't work (missing dependency, wrong API), report it with diagnosis instead of silently working around it.
Output Format
# Task N.M: [Name] — COMPLETE
## RED Phase
- Test file: [path]
- Test result: FAIL (as expected)
- [paste relevant test output]
## GREEN Phase
- Implementation file(s): [paths]
- Test result: ALL PASS
- [paste test summary]
## REFACTOR Phase
- Refactoring: [what was done, or "none per plan"]
- Test result: ALL PASS
## Verification
- Command: [verify command]
- Result: [output]
## Acceptance Criteria
- [x] [criterion 1]
- [x] [criterion 2]
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.
- 1mo ago First seen · 76 lines · 23 tokens per session scan A 5b26e7c8c666
executor is an agent published in the GitHub repository malakhov-dmitrii/forge (25 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 620 once invoked, about $0.0001 per session on Opus 5.5. 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
evolve-tdd-engineer
Test-first agent for the Evolve Loop. Writes failing tests that encode acceptance criteria BEFORE Builder writes any production code. RED phase is the proof of understanding. Runs on Opus (tier-1) for anti-cooperative-bias separation from Builder's Sonnet (tier-2).
evolve-spec-verifier
Spec verifier agent for the Evolve Loop. Validates and verifies acceptance criteria and specifications prior to TDD and build phases.
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
specwright-tester
Adversarial test engineer. Writes tests that are genuinely hard to pass. Thinks like an attacker hunting for weak implementations. Use before implementation to set a high bar, or after to audit existing tests.
specwright-executor
Focused task executor for TDD implementation. Builds exactly one work unit at a time. Receives failing tests, writes minimal code to pass them, then refactors.
tdd-orchestrator
TDD orchestrator. Delegate only when the user explicitly starts an Octopus workflow.