No schema drift on tracked dimensions (16 frontmatter fields, 5 built-in
agents). Routine version-bump from v2.1.121.
Co-Authored-By: Claude <noreply@anthropic.com>
Adds a Learnings entry to the GDG presentation agent capturing
(1) the etymology line just added to slide 13, (2) the actual
data-slide value of the horse-harness analogy slide in this deck so
future cross-deck syncs can reference it, and (3) a forward-looking
rule for cross-deck mirroring: when an edit lands on the sister
best-practices deck and the same slide exists here (i.e. inherited
from the original fork), evaluate whether to mirror — generic content
mirrors cleanly, event-specific content does not. Also notes that
slides should be located by content, not by trusting "slide N", since
post-fork drift can shift numbering between the two decks.
Co-Authored-By: Claude <noreply@anthropic.com>
Adds the same Old French etymology line ("The origin is Old French
harneis — gear, equipment, armor.") that was added to the canonical
best-practice deck, so the horse-harness analogy slide reads
identically across both decks. The line sits below the existing red
subtitle as a muted footnote (0.95rem, #666), with `text-align:
center` added for this deck because the GDG caption block relies on
flex centering rather than inherited text alignment.
Co-Authored-By: Claude <noreply@anthropic.com>
Adds a Learnings entry for the 2026-04-30 slide-10 insert: documents
the styled-HTML approach chosen (no PNG asset existed for this dialog),
the slide-12 caption-strip pattern reuse, and a postmortem for the
sentinel-replacement collision where pre-resolving ##S10## to "11" before
running the n=11..48 loop double-incremented old-slide-10 to "12". Adds
two forward-looking rules: (1) use distinct sentinel prefixes or
single-pass resolution when mixing pre-resolved and loop-resolved slides,
and (2) check raw file content for literal apostrophes vs HTML entities
when pattern-matching comment strings.
Co-Authored-By: Claude <noreply@anthropic.com>
Adds a styled-HTML dialog diagram (User vs Model bubbles, dashed amber
divider labeled "new session — context wiped", and a two-line caption
strip) to make the stateless behavior of LLMs visible. Drawn rather than
imported as PNG, mirroring slide-12's inline-diagram conventions. Old
slides 10..48 shifted to 11..49 via sentinel-replacement; banner
comments updated in the same pass to keep the deck's zero-drift state.
No new CSS classes — all layout via inline styles consistent with
surrounding slides.
Co-Authored-By: Claude <noreply@anthropic.com>
Appends a Learnings entry to the presentation-claude-gemini agent capturing
the 2026-04-30 removal of "How the Harness Reaches the World" from the GDG
deck and the deliberate-divergence framing — the slide lives on in the
forked claude-code-best-practice deck but is gone from the GDG historical
record because it was added post-event.
Future runs by this agent will know why the two decks differ on this slide
and won't try to "reconcile" them.
Co-Authored-By: Claude <noreply@anthropic.com>
The slide titled "Tool Calling" / "How the Harness Reaches the World" was
added to the deck after the GDG Kolachi event on Apr 25, 2026, so it doesn't
belong in the historical record of what was actually presented. Reverting
the GDG deck to as-presented state.
The slide is preserved in the new claude-code-best-practice fork (which is
the canonical living reference owned by presentation-claude-code), so no
content is lost overall — this is a deliberate divergence between the two
decks.
Slide had no data-level, so the journey bar is structurally unaffected.
Renumbered slides 15..53 → 14..52 via sentinel-replacement. Final count: 52.
Co-Authored-By: Claude <noreply@anthropic.com>
Updates the per-presentation delegation rule to route requests on the new
"Claude Code Best Practice" deck to the new presentation-claude-code agent.
Previously the table had only two decks (vibe-coding, claude-gemini); now
all three are listed with explicit path → agent mapping and an invocation
example.
Adds clarification that "the main presentation" or "the best-practice deck"
generally refers to the new claude-code agent.
Co-Authored-By: Claude <noreply@anthropic.com>
New per-deck agent owns presentation/claude-code-best-practice/index.html.
Mirrors the per-presentation pattern of presentation-claude-gemini and
presentation-vibe-coding — each deck has its own focused knowledge base
that self-evolves without cross-contaminating the others.
Seeded with structural facts about this deck specifically (no journey bar,
no hardcoded goToSlide(N) calls, simpler than the GDG fork) and a fresh
Learnings section starting at the 2026-04-30 fork date — GDG agent's 25+
historical entries deliberately not copied since most are tied to features
this deck doesn't have.
Co-Authored-By: Claude <noreply@anthropic.com>
Forked from presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html
on 2026-04-30 to serve as the ongoing main reference deck. Renamed and decoupled
from GDG/Gemini-specific branding:
- title tag, slide-1 H1, subtitle, and HTML banner all read "Claude Code Best Practice"
- favicon swapped from gemini-jumping.svg to claude-jumping.svg
- right-corner global Gemini mascot removed (left Claude mascot kept)
- GDG event badge replaced with neutral GitHub repo badge
- four trailing Gemini-comparison slides removed (49, 50, 51, 52)
- co-presenter intro slide removed
- inline <!-- SLIDE N: ... --> banners fully repaired (1:1 with data-slide values)
Final deck: 48 slides ending with "Thank you" closing slide.
Co-Authored-By: Claude <noreply@anthropic.com>
Records mattpocock/skills bumps (★ 33k→36k, skills 17→18) overtaking
wshobson/agents (★ 35k→34k), plus VoltAgent curated count correction
(1,100+ → 930+ per actual README parse). anthropics/skills and
K-Dense-AI/scientific-agent-skills unchanged.
Co-Authored-By: Claude <noreply@anthropic.com>
Records README CONCEPTS table updates for Subagents (CLAUDE_CODE_FORK_SUBAGENT),
Hooks (updatedToolOutput), MCP Servers (alwaysLoad), Settings (Auto Mode Config
inline link), and Ultrareview (claude ultrareview subcommand). The recurring
/slash-commands stale URL claim remains INVALID per long-standing user decision.
Co-Authored-By: Claude <noreply@anthropic.com>
No drift on the two tracked dimensions (16 frontmatter fields, 5 built-in
agents). Records the user-requested enum value addition (xhigh) to the effort
field description.
Co-Authored-By: Claude <noreply@anthropic.com>
Records promotion of fewer-permission-prompts from changelog-only to bundled
skills table, with /en/commands as the authoritative source over /en/skills.
Co-Authored-By: Claude <noreply@anthropic.com>
Records the v2.1.121 settings update: alwaysLoad, sshConfigs, status line
fields, ~/.claude.json → settings.json file-scope migration, AI_AGENT and
OTEL_LOG_USER_PROMPTS env vars, bypassPermissions exemption, /effort xhigh,
\${CLAUDE_EFFORT}, and broken auto-mode anchor links. OTEL_LOG_TOOL_DETAILS
and OTEL_LOG_TOOL_CONTENT remain ON HOLD per Rule 8A/10B.
Co-Authored-By: Claude <noreply@anthropic.com>
Mirrors the v2.1.91 pattern when auto was added to permissionMode — the field
description now lists low / medium / high / xhigh / max to match official docs.
Co-Authored-By: Claude <noreply@anthropic.com>
Promoted from /en/commands canonical reference (the Skills Reference prose at
/en/skills still undercounts at 5). Count updated 5 → 6.
Co-Authored-By: Claude <noreply@anthropic.com>
Adds the fff3b0/ddf4ff color split to the Workflow column spec, asks
research agents to mark each step as (top) or (sub) in the structured
report, updates the Phase 3 execute step to map those markers to badge
colors, and makes the post-table legend mandatory via new Rule 11.
Co-Authored-By: Claude <noreply@anthropic.com>
Restores the sub-loop semantic that was lost when parenthetical
qualifiers were flattened. Steps that repeat inside a parent step
(e.g. test-driven-development inside subagent-driven-development,
bmad-create-story per story, team-fix until verified) now use
fff3b0 (soft yellow) instead of ddf4ff (light blue). A blockquote
legend below the table explains the convention.
Affected rows: Superpowers, Get Shit Done, BMAD-METHOD, Matt Pocock
Skills, oh-my-claudecode. The other 6 workflows are flat with no
sub-loops.
Co-Authored-By: Claude <noreply@anthropic.com>
Updates the /workflows:development-workflows command to require
HTML <img align="middle"> badges (so arrows align with badge
centers) and to forbid parenthetical sub-loops or English
qualifiers in the Workflow chain. Inner loop steps must be
listed as flat siblings.
Co-Authored-By: Claude <noreply@anthropic.com>
Switches each Workflow cell from markdown image syntax to HTML
<img align="middle"> so the → arrow sits at badge vertical center
instead of dropping to the text baseline below the badges. Also
removes the parenthetical sub-loops and English qualifiers (e.g.
"parallel waves + ... loop", "per story", "+ feedback-loops") that
were unparseable without upstream context — inner loop steps are
now just listed as siblings in the flat chain.
Co-Authored-By: Claude <noreply@anthropic.com>
Removes the Plan-implementation research item from both agent prompts,
strips the PLAN line from the structured report format, and prunes the
Plan-link rules from Phase 0/2/3 and the Rules section. Column order
in the spec now matches the README: Name | ★ | Workflow | a | c | s.
Co-Authored-By: Claude <noreply@anthropic.com>
The Plan column duplicated information already legible in the Workflow
pipeline (the entry skill is always the first badge in the row) and the
Workflow column carries more signal. New column order:
Name | ★ | Workflow | a | c | s.
Co-Authored-By: Claude <noreply@anthropic.com>
Each row's Workflow cell now renders the canonical end-to-end pipeline
as a sequence of ddf4ff shields.io badges joined by →, replacing the
former 2-3 adjective tags. Matt Pocock Skills inserted at rank 8 (36k ★)
in star-descending order.
Co-Authored-By: Claude <noreply@anthropic.com>
Records the initial seeding of the SKILL COLLECTIONS table from the
development-workflows-research-agent findings on 2026-04-28. Establishes
status legend so future /workflows:skill-collections runs can append
entries in the same format as changelog/development-workflows/.
Co-Authored-By: Claude <noreply@anthropic.com>
New section between DEVELOPMENT WORKFLOWS and TIPS AND TRICKS, listing 5
curated SKILL.md collection repos (anthropics/skills, wshobson/agents,
mattpocock/skills, scientific-agent-skills, awesome-agent-skills) sorted
by stars. Badge timestamp refreshed via /workflows:skill-collections
first-run; CLI version unchanged at v2.1.119.
Co-Authored-By: Claude <noreply@anthropic.com>
CLI version unchanged at v2.1.119; only the date/time fragment of the
shields.io badge is refreshed to reflect the latest README touch.
Co-Authored-By: Claude <noreply@anthropic.com>
- Swap intro-slide logos from disrupt-logo.png to disrupt.svg (lines 190 and 260)
- Wrap each disrupt logo in <a href="https://disrupt.com" target="_blank" rel="noopener noreferrer"> so the logo opens disrupt.com in a new tab
- Update model-limitation.jpg path from assets/model/ to assets/harness/ to match the asset move
- Insert new "Tool Calling" slide using assets/harness/tool-calling.png; cascading data-slide renumber for all 40 slides at index >= 13 (totals: 52 -> 53)
- Reorder slides 12-14 so the narrative reads Limitations -> Horse+Harness metaphor -> Tool Calling mechanism
Co-Authored-By: Claude <noreply@anthropic.com>
Visual aid showing how the model issues tool calls and the harness executes
them against the outside world. Used by the new Tool Calling slide.
Co-Authored-By: Claude <noreply@anthropic.com>
Vector replacement for the previous disrupt-logo.png raster, keeping crisp
rendering at any projection scale.
Co-Authored-By: Claude <noreply@anthropic.com>
Reorganize the screenshot under harness/ alongside other harness-limitation
assets. File contents unchanged (rename detected as 100% similarity).
Co-Authored-By: Claude <noreply@anthropic.com>
Append entry recording 9 applied actions (5 star bumps, 1 BMAD tag rewrite
22+ platforms→42 platforms, 3 count updates for Compound Engineering and
BMAD) plus 4 ON HOLD verify items for recurring API-vs-baseline drops
(ECC commands/skills, GSD commands, oh-my-claudecode skills, Superpowers
agents). The held items follow the established conservative pattern of
keeping the higher prior count when API enumeration drops aren't backed
by a release note.
Co-Authored-By: Claude <noreply@anthropic.com>
Append v2.1.119 entry recording 17 actions: Tasks row URL retargeted to
local report, Scheduled Tasks description disambiguated into 3 surfaces
(loop/schedule/desktop), Fast Mode added as Hot row (with Settings
side-link removed to avoid duplication), Auto Memory Deep-dive and Skills
for Mono-repos inline links added, plus 8 verification rows confirming
all CONCEPTS URLs/anchors stable. INVALID rows cover the recurring
/slash-commands redirect (kept by user) and incorrect agent reads of beta
status / minor concept additions.
Co-Authored-By: Claude <noreply@anthropic.com>
Shayan Rais