Three doc updates covering the AGENTS.md context-injection
pattern introduced in the previous commit.
CLAUDE.md — new "Project-scoped chat + Scarf-managed AGENTS.md
context (v2.3)" subsection under Project Templates. Covers:
- The session-project sidecar at ~/.hermes/scarf/session_project_map.json
(why it exists, what manages it)
- How Hermes picks up project context: cwd-based auto-load of the
first matching context file (priority order, 20KB cap)
- Exact marker format and block shape
- Invariants that future edits must preserve: secret-safe,
idempotent, bounded-region, non-fatal, refresh-before-session-start
ordering
- Template-author contract: leave the region alone, put
instructions below
- Known caveat: parent-directory `.hermes.md` shadowing (deferred
to v2.4)
scarf-template-author SKILL.md — new pitfall bullet in the
"Common pitfalls" checklist telling scaffolding agents to
preserve the `<!-- scarf-project -->` region and put template-
specific instructions below it. Rebuilt the bundle so installs
from the catalog pick up the guidance; regenerated catalog.json.
Wiki update (Project-Templates page) lands next via scripts/wiki.sh.
93/93 Swift + 24/24 Python tests pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pairs with the config-sheet wrap fix in d616935. Even though the
Configuration sheet now renders raw URLs correctly, markdown link
syntax reads cleaner in the form — the visible text is the label,
not the URL. Teaching this in SKILL.md prevents the scaffolding
skill from generating schemas that look worse than they could.
Additions to SKILL.md:
- New "Writing good descriptions" subsection under Config Schema
Design. Good/bad examples side by side; rule of thumb to wrap
long unbreakable strings (URLs, paths) in markdown links or
inline code.
- New item in the Common Pitfalls checklist: "No raw URLs in
field descriptions."
Bundle rebuilt, catalog.json regenerated. 24/24 Python tests
still pass; Python validator treats descriptions as opaque strings
so no validator changes needed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
A new .scarftemplate in the public catalog whose only content is
a Hermes skill that teaches an agent how to scaffold a new
Scarf-compatible project — dashboard, optional configuration
schema, optional cron job, AGENTS.md — from a short conversational
interview. Scaffolded projects are usable locally and cleanly
exportable as .scarftemplate bundles later.
The skill itself (~400 lines of structured markdown at
skills/scarf-template-author/SKILL.md) covers:
- When to invoke vs. when to answer inline
- The on-disk project shape Scarf expects
- A 5-question interview flow
- Full widget catalog (all 7 widget types) with JSON shapes
- Config schema design + hard invariants (no defaults on secrets,
`contents.config` must match field count, etc.)
- Cron-job design including the {{PROJECT_DIR}} gotcha
- Step-by-step file writing (dashboard, manifest, AGENTS.md, README)
- Testing + catalog validation instructions
- Common pitfalls + source-of-truth references
Delivered as a .scarftemplate so the install flow's normal
safeguards apply: preview sheet shows one project + one skill
+ zero cron jobs + no config step, uninstall drops both the
project dir and the namespaced skill folder via the existing
lock-file mechanism.
Scope per user sign-off: blank-slate / fully conversational for
v1. Pre-baked archetypes (`monitor`, `dev-dashboard`, etc.) are
deferred to v1.1 pending real usage data on what shapes users
actually ask for.
New Swift test exercises the bundle through the installer's
plan builder — asserts manifest shape, that the skill lands at
~/.hermes/skills/templates/awizemann-template-author/scarf-template-author/SKILL.md,
and that no-config templates correctly skip the manifest cache.
58/58 Swift tests pass; 24/24 Python tests pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Alan Wizemann