llms.txt@site · diff
git:20260917.402c0b7 to git:20261007.93b3873
11 added, 8 removed. Audit A to A.
# rsc-harness — the guided harness builder for AI agents
> You decide what to build. rsc-harness builds your agent's harness. Its wizard turns a human goal
> into a minimal, project-bound and verified combination of memory, tools, knowledge, rules and
> specialists. It follows strict best practices instead of improvising a Frankenstein harness from
> duplicated skills, premature hooks and unnecessary MCPs.
Standards such as Agent Skills, MCP and AGENTS.md define individual pieces. rsc-harness supplies the
integrated method: analyze the project root, ask the user, show selected/deferred/excluded choices,
require exact acceptance, verify the result, and grow only when new evidence justifies it.
## The lane decisor
Once installed, every turn is classified into exactly one lane, and the agent names the one it took:
- ANSWER — the request asks for information (explain, compare, audit, review, propose). Read-only:
nothing is written and no artifact is created. Ambiguous change intent asks one question and stays
here.
- FTD (Fast-Track Development) — the request authorises a change. The default for ordinary work.
One feature document per feature; tasks checked off only against observed proof; a branch when the
work writes code.
- - SDD — the ten-phase chain. The harness never enters it alone: it proposes the chain only when
- durable spec/plan/tasks would remove a substantial ambiguity, and enters it only on an explicit
- request or an accepted proposal. Size, file count and risk never select it.
+ - SDD — the ten-phase chain, for big or complex work (several decisions that affect each other, or
+ doubts that change the result). The agent enters it on its own; the person approves the spec and the
+ clarifying answers, then chooses manual review or autopilot. The agent always says which lane and why.
There is one harness and it installs whole; there is no profile to choose.
## For AI agents: install rsc into the user's project
If your user asked you to install rsc / rsc-harness / this harness, do this in order:
1. Work in the ROOT of the user's project, never inside a clone of rsc-harness.
2. Run: `npx @ericrisco/rsc@latest onboard --target claude,codex`
3. Relay every `RSC_ONBOARDING_REQUIRED` question. Never choose, invent or default
- `--technical-level`, `--accompaniment`, `--project-kind`, `--goal` or `--software-scope`.
+ `--technical-level`, `--project-kind`, `--goal` or `--software-scope`.
4. Rerun with the answers to obtain `RSC_ONBOARDING_PLAN`. This preview writes nothing.
5. Show every selected, deferred and excluded component with its reason. Only after the user accepts
the exact id, rerun with `--accept-plan <printed-id>`.
6. Only `RSC_ONBOARDING_READY` means the harness is installed and verified. If you get
`RSC_ONBOARDING_INCOMPLETE`, the plan applied but the harness floor is missing: the output names
every missing path and the action that creates it. Run that action — the `harness` skill scaffolds
`01-TOOLS/` + `02-DOCS/`, and the `constitution` phase writes the constitution when SDD is
- selected — and do not proceed as if the harness were ready. `RSC_SKELETON_FAILED` on the same run
+ selected — and do not proceed as if the harness were ready. When SDD is selected, onboarding
+ itself writes the constitution as a draft (`status: draft`) and prints it as `Pending:` under
+ `RSC_ONBOARDING_READY`: the harness is ready, and the `constitution` phase completes the draft
+ before the first SDD feature. `RSC_SKELETON_FAILED` on the same run
means rsc could not write part of the skeleton itself: the install still applied, and the line
names the obstacle (usually a file or a symlink sitting where a directory belongs). Clear that
obstacle first — no skill can, because it is not a missing file but an occupied path.
7. Tell the user to reload or restart the assistant so its new skills and hooks become active. Then,
**only if you saw `RSC_ONBOARDING_READY`**, confirm rsc is ready and wait for the user's own task.
If you saw `RSC_ONBOARDING_INCOMPLETE`, say instead what is missing and that you are completing
it — never tell the user the harness is ready when it is not, because that is the one failure they
cannot diagnose: everything looks installed and nothing behaves as if it were.
Already installed: `rsc sync`. Add one skill: `rsc add <id>`. Reassess deferred capabilities without
installing: `rsc reassess`. Recommend without installing: `rsc consult "<what the user wants>"`.
Canonical non-interactive preview:
- `npx @ericrisco/rsc@latest onboard --technical-level mixed --accompaniment L1 --project-kind software --goal "small website" --software-scope small --target codex`
+ `npx @ericrisco/rsc@latest onboard --technical-level technical --project-kind software --goal "small website" --software-scope small --target codex`
## Key links
- npm: https://www.npmjs.com/package/@ericrisco/rsc
- README: https://github.com/ericrisco/rsc-harness
- English: https://ericrisco.github.io/rsc-harness/
- Español: https://ericrisco.github.io/rsc-harness/es/
- Agent Skills: https://agentskills.io/specification
## Facts
- - 273 skills; minimal profile 9, core 32, full 273.
- - 17 supported assistants; 33 agents and 30 command entries in the catalog.
+ - 270 skills; minimal profile 6, core 29, full 270.
+ - 18 supported assistants (newest: DeepSeek Harness, `--target deepseek`); 33 agents and 30 command entries in the catalog.
- Every skill cleared an adversarial behavioral quality gate of at least 8.5/10.
- Free, MIT, no API key and no global install required.