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 skills add nestharus/agent-implementation-skill --skill srcgit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWrote 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/skills/nestharus/agent-implementation-skill/src)<a href="https://agentmods.dev/skills/nestharus/agent-implementation-skill/src"><img src="https://agentmods.dev/badge/skills/nestharus/agent-implementation-skill/src/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/skills/nestharus/agent-implementation-skill/src"><img src="https://agentmods.dev/badge/skills/nestharus/agent-implementation-skill/src.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 | $0.00086 | $0.03777 |
| Opus 5.5 | $0.00034 | $0.01511 |
| Sonnet 5.5 | $0.00017 | $0.00755 |
| Haiku 4.5 | $0.00009 | $0.00378 |
Grade C, and why
agent-implementation-skill scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Clean up planspace when workflow is fully complete (`rm -rf` the workspace dir). How it starts
The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow
Single entry point for the full development lifecycle. Read this file, determine what phase you're in or what the user needs, then read the relevant sub-file from this directory.
Paths
Everything lives in this skill folder. WORKFLOW_HOME is: !dirname "$(grep -rl '^name: agent-implementation-skill' ~/.claude/skills/*/SKILL.md .claude/skills/*/SKILL.md 2>/dev/null | head -1)" 2>/dev/null
When dispatching scripts or agents, export WORKFLOW_HOME with the path
above. Scripts also self-locate via dirname as a fallback when invoked
directly.
$WORKFLOW_HOME/
SKILL.md # this file — entry point
implement.md # multi-model implementation pipeline
research.md # exploration → alignment → proposal
rca.md # root cause analysis
evaluate.md # proposal review
baseline.md # constraint extraction
audit.md # concern-based problem decomposition
constraints.md # constraint discovery
models.md # model selection guide
scripts/
workflow.sh # schedule state markers ([wait]/[run]/[done]/[fail]) — internal, not the entry point
db.sh # SQLite-backed coordination database
tools/
extract-docstring-py # extract Python module docstrings
extract-summary-md # extract YAML frontmatter from markdown
README.md # tool interface spec (for Opus to write new tools)
<system>/agents/ # agent definitions distributed across system modules (scan/, proposal/, implementation/, verification/, testing/, etc.)
templates/
implement-proposal.md # 10-step implementation schedule
research-cycle.md # 7-step research schedule
rca-cycle.md # 6-step RCA schedule
Workspaces live on native filesystem for performance, separate from project:
- Planspace:
~/.claude/workspaces/<task-slug>/— schedule, state, log, artifacts, coordination database - Codespace: project root — where source code lives
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _config.py 291 B runs code
- agent_implementation_skill.egg-info/dependency_links.txt 1 B
- agent_implementation_skill.egg-info/entry_points.txt 90 B
- agent_implementation_skill.egg-info/PKG-INFO 238 B
- agent_implementation_skill.egg-info/requires.txt 38 B
- agent_implementation_skill.egg-info/SOURCES.txt 316 B
- agent_implementation_skill.egg-info/top_level.txt 1 B
- audit.md 3.9 KB
- baseline.md 3.1 KB
- bootstrap/__init__.py 263 B runs code
- bootstrap/agents/codemap-builder.md 4.3 KB
- bootstrap/agents/decomposer.md 10 KB
- bootstrap/agents/entry-classifier.md 6.1 KB
- bootstrap/agents/factor-explorer.md 12 KB
- bootstrap/agents/problem-explorer.md 10 KB
- bootstrap/agents/problem-extractor.md 8.5 KB
- bootstrap/agents/proposal-aligner.md 10.0 KB
- bootstrap/agents/proposal-expander.md 11 KB
- bootstrap/agents/reliability-assessor.md 12 KB
- bootstrap/agents/section-explorer.md 3.3 KB
- bootstrap/agents/substrate-discoverer.md 2.6 KB
- bootstrap/agents/user-researcher.md 12 KB
- bootstrap/agents/value-explorer.md 12 KB
- bootstrap/agents/value-extractor.md 12 KB
- bootstrap/routes.py 3.7 KB runs code
- constraints.md 3.2 KB
- containers.py 25 KB runs code
- coordination/__init__.py 317 B runs code
- coordination/agents/bridge-agent.md 2.1 KB
- coordination/agents/consequence-note-triager.md 2.6 KB
- coordination/agents/coordination-fixer.md 5.6 KB
- coordination/agents/coordination-planner.md 7.1 KB
- coordination/agents/recurrence-adjudicator.md 2.3 KB
- coordination/agents/scaffolder.md 4.3 KB
- coordination/engine/__init__.py 0 B runs code
- coordination/engine/coordination_controller.py 11 KB runs code
- coordination/engine/global_coordinator.py 26 KB runs code
- coordination/engine/plan_executor.py 29 KB runs code
- coordination/problem_types.py 3.5 KB runs code
- coordination/prompt/__init__.py 0 B runs code
- coordination/prompt/writers.py 12 KB runs code
- coordination/repository/__init__.py 0 B runs code
- coordination/repository/notes.py 1.9 KB runs code
- coordination/repository/scope_deltas.py 453 B runs code
- coordination/routes.py 799 B runs code
- coordination/service/__init__.py 0 B runs code
- coordination/service/completion_handler.py 13 KB runs code
- coordination/service/decision_recorder.py 1.6 KB runs code
- coordination/service/planner.py 11 KB runs code
- coordination/service/problem_resolver.py 14 KB runs code
- coordination/service/stall_detector.py 2.2 KB runs code
- coordination/types.py 2.9 KB runs code
- dispatch/__init__.py 419 B runs code
- dispatch/agents/agent-monitor.md 2.9 KB
- dispatch/agents/bridge-tools.md 2.5 KB
- dispatch/agents/tool-registrar.md 4.3 KB
- dispatch/engine/__init__.py 0 B runs code
- dispatch/engine/agent_executor.py 6.9 KB runs code
- dispatch/engine/section_dispatcher.py 9.9 KB runs code
- dispatch/helpers/__init__.py 0 B runs code
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 · 338 lines · 86 tokens per session scan C 8a6024387193
agent-implementation-skill is a skill published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 13d ago), licensed MIT. It adds 86 tokens to every session and 3,777 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
soul
Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
gmx-liquidity
Provide liquidity on GMX V2 — deposit into GM pools and GLV vaults, withdraw, shift between pools, and query pool data across Arbitrum, Avalanche, and Botanix.
gmx-trading
Trade perpetuals and swap tokens on GMX V2 — a decentralized exchange with oracle-based pricing on Arbitrum, Avalanche, and Botanix. Supports market/limit/stop orders, leverage up to 100x, and programmable position management via TypeScript SDK or REST API.
excalidraw
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .excalidraw files and exports to PNG/SVG via Kroki API or locally using…
test-driven-development
Strict red-green-refactor TDD workflow for implementing features, fixing bugs, or changing behavior in Rails applications. Enforces the discipline of writing a failing test before any production code. Use whenever you want to implement with TDD — whether a new feature, a bugfix, a refactor, or any behavior change.