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>
Codify the new check surfaced this run: README ![beta] badges in the Hot
table should still match the upstream docs page banner (research preview,
experimental, env-var gated). Origin: workflow-concepts-agent flagged
Routines, No Flicker Mode, Computer Use, and Code Review as candidates;
re-verification confirmed all four still legitimately carry beta status,
but the drift type wasn't covered by existing description-currency rules.
Co-Authored-By: Claude <noreply@anthropic.com>
Append v2.1.119 entry covering all settings/env-var/CLI changes applied to
claude-settings.md: prUrlTemplate, voice object expansion, auto permission
mode rewrite, blockedMarketplaces hostPattern/pathPattern enforcement,
CLAUDE_CODE_HIDE_CWD env var, claude plugin tag CLI, MCP OAuth callout,
and Quick Reference example. Includes 4 ON HOLD/INVALID rows for recurring
items (OTEL_LOG_*, schemastore redirect, agent-flagged false drift).
Co-Authored-By: Claude <noreply@anthropic.com>
Append v2.1.119 entry confirming all 16 frontmatter fields and 5 built-in
agents remain in sync with official docs.
Co-Authored-By: Claude <noreply@anthropic.com>
Append v2.1.119 entry confirming frontmatter (15 fields) and bundled
skills (5) remain synchronized with official docs.
Co-Authored-By: Claude <noreply@anthropic.com>
Settings additions:
- prUrlTemplate (Attribution): URL template for the PR badge in commit
attribution — supports self-hosted GitLab/Bitbucket/GitHub Enterprise
- voice (object): full structure with enabled/mode/autoSubmit; mark legacy
voiceEnabled as DEPRECATED alias
Behavior updates:
- auto permission mode: rewrite per official docs — drop the removed
--enable-auto-mode flag, note inclusion in the default Shift+Tab cycle
since v2.1.111
- blockedMarketplaces: note v2.1.119 enforcement of hostPattern/pathPattern
matchers before any download touches the filesystem
Env var additions:
- CLAUDE_CODE_HIDE_CWD: hides CWD in startup logo banner (v2.1.119)
CLI / docs additions:
- claude plugin tag: marketplace plugin version tagging subcommand (v2.1.118)
- MCP OAuth callout: RFC 9728 protected-resource discovery, no manual
apiKeyHelper/headersHelper needed for compliant servers (v2.1.111)
- Quick Reference example updated with prUrlTemplate
Bump Last Updated badge and version header to v2.1.119.
Co-Authored-By: Claude <noreply@anthropic.com>
- /branch: note CLAUDE_CODE_FORK_SUBAGENT env var causes /fork to spawn a
forked subagent instead of branching the conversation (v2.1.117)
- /focus: clarify "Only available in fullscreen rendering" (v2.1.110)
- /skills: add "Press t to sort by token count" (v2.1.110/111)
- /clear: reword to contrast with /compact — /clear starts fresh, /compact
preserves the same conversation
- Bump Last Updated badge and version to v2.1.119
Co-Authored-By: Claude <noreply@anthropic.com>
No drift detected — all 16 frontmatter fields and 5 built-in agents match
v2.1.119 docs. Badge-only refresh.
Co-Authored-By: Claude <noreply@anthropic.com>
No drift detected — frontmatter fields (15) and bundled skills (5) are fully
synchronized with v2.1.119 docs. Badge-only refresh.
Co-Authored-By: Claude <noreply@anthropic.com>
Shayan Rais