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 iwe-org/dev-workspace --skill implementgit clone --depth 1 https://github.com/iwe-org/dev-workspaceWrote 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/iwe-org/dev-workspace/implement)<a href="https://agentmods.dev/skills/iwe-org/dev-workspace/implement"><img src="https://agentmods.dev/badge/skills/iwe-org/dev-workspace/implement/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/iwe-org/dev-workspace/implement"><img src="https://agentmods.dev/badge/skills/iwe-org/dev-workspace/implement.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 | $0.00066 | $0.00751 |
| Opus 5.5 | $0.00026 | $0.00300 |
| Sonnet 5.5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
implement 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement a plan
Coding happens as it always does; this skill adds the discipline that keeps the plan document true while it happens. The plan is the source of truth: the code follows it, and where reality wins an argument, the plan is updated — never silently outgrown.
Steps
- Select the plan. Infer from conversation; if ambiguous, list the plans
under
## Activeindata/plans.mdand ask (most recently created first). Announce: "Working on: — task N of M". No plan exists for what the user wants built? Stop and point at the plan skill. - Load the context. Read the full plan, the specs in its
## Spec changes, anddata/product.md## Constraintsand## Authoring rules— they bind the code you're about to write. - Check
## Depends on. Every prerequisite plan must carrystage: done; if one doesn't, say so and stop — building on an unshipped dependency is how two plans end up half-true. - Re-verify the anchors. The plan's
## Key referencesline numbers were true when written; re-locate each symbol in the current checkout before relying on it. If lines moved, update the anchor list and its "verified as of" date — that edit is part of this session's work. - Execute the next unchecked task. Follow its
**Files:**list; write the code; run the tests that cover this task. When the task's work is done and its tests pass, tick its- [ ]→- [x]in the plan doc andiwe normalize. - Write back deviations. If implementation reveals the
## Approach(or a task breakdown) is wrong, update the plan — amend the section, add or split tasks — before coding past the discrepancy, and tell the user what changed and why. - Stop at a clean boundary. After each task (or more, if the user asked for a longer run), report progress — "3/5 tasks, next: " — and stop. Blocked mid-task? Leave the box unchecked, describe the blocker, and stop there instead.
- Finish. When the last box ticks, run the plan's
## Verificationcommands, report the results, and suggest the verify skill for the full pre-ship check, then the ship skill.
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 · 56 lines · 66 tokens per session scan A f8723adfb07d
implement is a skill published in the GitHub repository iwe-org/dev-workspace (10 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 751 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
context-engineering
A guide to organizing the instructions and information an AI agent receives at each step. It covers system prompts, tool descriptions, conversation history, on-demand skills, and protections against unsafe outside content.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
loop-engineering
A guide to building reliable loops for AI agents that plan, act, check their work, and continue until a task is truly complete. It includes independent verification and a proposer-reviewer pattern in which one agent's work is checked using outside evidence.
multi-agent-design
A guide to deciding when several AI agents should work together and how they should share tasks, context, and files. It compares peer, manager-led, and decentralised arrangements and explains common coordination failures.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.