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 agentmods add skills/qwerfunch/cladding/developernpx skills add qwerfunch/cladding --skill developergit clone --depth 1 https://github.com/qwerfunch/claddingWhat 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 | $0.00051 | $0.01296 |
| Opus 5 | $0.00026 | $0.00648 |
| Sonnet 5 | $0.00010 | $0.00259 |
| Haiku 4.5 | $0.00005 | $0.00130 |
Grade A, and why
developer 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer
The Developer is a selectable role brief (formerly specialists) — the implementer. cladding declares this scope and its evidence obligations; the host embodies it with any agent shape. You write source under src/stages/, spec/ (helpers, not yaml), src/hitl/, and tests/.
See docs/ssot-model.md for the 4-tier SSoT model.
Sources (what you read, by Tier)
| Tier | Artifacts | Why you read it |
|---|---|---|
| B | docs/project-context.md |
intent / Why/What/Purpose to align implementation |
| B | spec/architecture.yaml |
layer boundary check when placing new modules |
| B | spec/capabilities.yaml |
user-facing surface this feature maps to (for capability features[] binding) |
| C | docs/conventions.md |
code style: indent, naming, error handling, test location |
| A | current feature slice only, never the whole spec | what to build |
You do NOT read Tier D (audit — observability's concern).
Boundary
| what you do | what you don't |
|---|---|
| Write code · tests · migrations | Modify spec.yaml (that's planner) |
Run npm test · npm run stage:* |
Sign off on your own code (that's reviewer) |
| Refactor for clarity | Bypass the Iron Law gates |
| Add new stage runners | Invent new evidence shapes (the schema is fixed) |
Code policy
Follow docs/conventions.md — clad init always writes it. The auto-generated header at the top of the file tells you which mode is active:
- Greenfield seed: toolchain-default 14-signal table (per-language defaults) with the canonical style-guide URL inlined. Use these defaults until you have written enough code that
clad init --scancan replace them with observed values. - Observed: the 14-signal table reflects what the scanner found in your code. Follow it verbatim.
One cladding-specific addition on top of either mode:
- Error as Data — return
{pass, exitCode, stderr?}shapes, not throws (except boundaries)
Anti-self-cert reminder
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.
- yesterday First seen · 86 lines · 51 tokens per session scan A 3002b4ef69dd
developer is a skill published in the GitHub repository qwerfunch/cladding (14 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 1,296 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 2026-08-30.
Other skills, from other repositories
map-plan
ARCHITECT phase - decompose complex tasks into atomic subtasks with research, spec, and branch-scoped plan artifacts under .map.
map-review
Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.
map-debug
Structured MAP debugging via task-decomposer, actor, and monitor agents. Use when reproducing a bug, isolating a regression, or diagnosing an error with specialized agents — including failing or flaky tests (pytest AssertionError), crashes and segmentation faults, memory-corruption or memory errors in native/C…
map-learn
Capture reusable lessons after a completed MAP workflow. Use when a MAP run has finished and you want rules written to .claude/rules/learned/ from a workflow summary or handoff. Do NOT use during active implementation.
map-efficient
State-machine MAP execution workflow for Codex. Use when implementing an approved MAP plan end to end, resuming from branch MAP taskplan or stepstate.json artifacts, or running non-trivial multi-subtask work. Use map-fast for tiny one-shot edits.
map-task
Execute a single subtask from an existing MAP plan via Actor and Monitor. Use when map-plan has decomposed work and you want fine-grained control over one subtask. Do NOT use without an existing plan; run map-plan first.