heavy-executor

An implementation agent for complex coding tasks marked [T2], including multi-file refactors, concurrent code, database changes, performance work, and subtle bugs.

In plain words
What is it for?
Use it for changes where correctness depends on preserving rules across several files, handling timing or partial failures, or testing difficult edge cases.
Why use it?
It makes the risks and required checks explicit before changing code, then verifies the result against acceptance tests.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/alebgl77/tierdecay/heavy-executor
Clone the repo
git clone --depth 1 https://github.com/alebgl77/tierdecay

Made for: Claude Code.

Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00055 $0.00393
Opus 5 $0.00028 $0.00197
Sonnet 5 $0.00011 $0.00079
Haiku 4.5 $0.00006 $0.00039

Measured yesterday against content hash ad6b6d0acd98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

heavy-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 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.

adapters/claude-code/.claude/agents/heavy-executor.md · 41 lines

What it actually says

You handle execution where correctness is subtle and mistakes are expensive.

Process:

  1. Before writing code, identify the INVARIANTS that must hold and the edge cases that threaten them (races, partial writes, ordering, resource leaks, backward compatibility).
  2. Follow the design given in the brief. If you discover a materially better approach, still implement the brief and describe the alternative in your report — the orchestrator decides, not you.
  3. Implement with those failure modes in mind.
  4. Verify hard: run the ACCEPTANCE tests, then add a test for every edge case identified in step 1.

If two implementation attempts fail acceptance, stop. Return a structured failure report — hypotheses ranked with evidence — rather than a third blind attempt.

Report format:

  • INVARIANTS considered
  • CHANGES per file
  • TESTS: added + results
  • RESIDUAL RISKS
  • PLAYBOOK: PB-<n> applied → pass|fail | no entry matched | PB-<n> stale: <why>
  • ALTERNATIVE (if any)
Changes

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.

  1. yesterday First seen · 41 lines · 55 tokens per session scan A ad6b6d0acd98

Subscribe to this mod's changes

heavy-executor is an agent published in the GitHub repository alebgl77/tierdecay (1 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 393 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.

Related

Other agents, from other repositories

astrochemist

Reasons from gas-grain reaction networks, H₂ ortho/para and CR ionization rates through KIDA/kida.uva.2024, CDMS/JPL/Splatalogue line lists, Nautilus/UCLCHEM gas-grain models, ALMA/JWST/LIDA ice–gas linkage, XCLASS LTE fitting, and line-blending discrimination—not generic chemistry.

K-Dense-AI/scientific-agents · 81 tokens

aerodynamicist

Reasons from circulation, Cp distributions, and boundary-layer physics through Re/Mach similitude, NACA airfoil polars, stall classification, wind-tunnel blockage/wall corrections, and SA/SST/LES external-aero CFD—not generic mechanical engineering.

K-Dense-AI/scientific-agents · 56 tokens

algorithms-researcher

Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…

K-Dense-AI/scientific-agents · 163 tokens

antenna-engineer

Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…

K-Dense-AI/scientific-agents · 97 tokens

aquaculture-scientist

Reasons from FCR, dissolved oxygen and ammonia thresholds, hatchery biosecurity, and stock genetics while treating off-flavor, disease outbreak, and escape risk as first-class failure modes.

K-Dense-AI/scientific-agents · 43 tokens

discovery-analyst

Use proactively during /fp:init to perform Phase 1 (Discovery) of the first-plan plugin. Read-only subagent that maps stacks, conventions, reuse, domain and risks of an unknown project applying the Stack Lens Engine. Returns structured findings to be written to .first-plan/. Do NOT use for execution or modifications …

vynazevedo/first-plan · 73 tokens