CLAUDE.md and GEMINI.md existed as per-runtime extensions of AGENTS.md, and
only one of them carried anything at all: GEMINI.md stated that it had no
additions, while CLAUDE.md held rules that bind every runtime anyway — the
permission announcement, the make-over-raw preference, the loop, chain and
heredoc bans, the stream-the-log-to-/tmp rule, the CI-evidence rule, the push
ban and the comment rule. A rule that binds every agent does not belong in one
agent's file. AGENTS.md absorbs them and now states that no tool-specific
extension file exists; agents whose runtime auto-loads a different filename
reach it through their own configuration instead.
The filenames were machinery as much as prose. The PR templates, the branch
and pull-request scope tables, the settings and security docs that justified
the loop deny by "the textual CLAUDE.md rule", six requirement documents whose
push instruction linked ../../CLAUDE.md, and a test docstring citing the
shell-loop ban all named them, and now name AGENTS.md.
scripts/meta/resolve/pr/scope.sh deliberately keeps matching CLAUDE.md and
GEMINI.md: this change deletes them, and without those patterns the change
itself would not classify as agent-scope.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
A deploy log carries provisioning secrets in argv and environment dumps,
and reading one by line range puts them in the transcript verbatim. The
rule requires extracting the named field instead, states that a secret
denylist is not protection because it is case-sensitive and secrets also
ride inside URL paths, and records that no_log does not help locally
because MASK_CREDENTIALS_IN_LOGS is disabled there.
Move the operator cheatsheet's copy-paste prompts into per-workflow i8- skills
that each route to their authoritative procedure doc, and reduce the cheatsheet
to a table index plus a usage paragraph, enforced by a new lint. Add skills for
develop, test, quality, refactor, the debug and requirement flows, and
commit / pull-request / push-trigger-pull; rename the iteration skills to
i8-iterate-* and rename the index to i8-help. Wire the active-listening,
dialectic, and robot skills into the flows for clarification, uncertain root
causes, and autonomous execution. Drop the Infinito-specific agent aliases
(alias.md, INFINITO_ALIAS_MD, the make alias agent section, and the two alias
tests); terminal aliases stay.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replace the bracket tag with the sentence form so the hint teaches the
shorter alias in place: Speed up by using prompt/cli alias X instead of
what the operator wrote.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add the i8* terminal aliases (make install-alias) and ai8* agent
conversation shortcuts (docs/.../agents/alias.md), move skill
distribution to the external INFINITO_SKILLS_REPOSITORY (make
install-skills), and add make cheat, make alias and make onboard. Introduce
custom.env operator overrides (win over defaults and handlers) and pin
INFINITO_ALIAS_MD / INFINITO_ALIAS_REPOSITORY / INFINITO_SKILLS_REPOSITORY
in default.env. Drop the in-repo skills-lock.json and its update-skills CI
job. AGENTS.md instructs agents to suggest the matching cli/prompt alias
when an operator writes something an alias covers. Lints enforce alias
sorting, i8/ai8 prefixes, no consonant clusters, full make-target
coverage, and terminal/agent shortcut non-overlap.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Three classes of drift cleaned up across 85 .md files:
- Em-dashes: replaced ` — ` with the contextually correct separator
(colon for `term: explanation`, period to split clauses across
sentences/source lines, parentheses for asides, semicolon for
tight-linked continuations). Two intentional exceptions remain
in `docs/contributing/documentation.md` (the rule literal) and
inside a fenced ```sh block in `docs/contributing/actions/debugging/ci.md`.
- SPOT self-labels: rewrote "This is the SPOT for X" to describe
the subject directly ("This directory holds X" / "This file
describes X"). Cross-references to other artefacts' canonical
role remain unchanged.
- Heading-emoji position: moved leading-emoji headings (`# 🧩 Title`)
to trailing position (`# Title 🧩`) per the headline rule that
emojis MUST come after the title text.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
AGENTS.md:
- Replace "SPOT" with "single source of truth"
- Split loading rules: CONTRIBUTING.md, docs/contributing/ walk, docs/agents/ walk — each an explicit MUST
- Add Tool-Specific Extensions section binding Claude Code → CLAUDE.md, Gemini CLI → GEMINI.md
- Extend reload trigger to cover tool-specific extension file
- Make sandbox.network bullet prescriptive (replace "govern" with conditional MUSTs)
- Drop architectural description from permission model intro
- Fix Temporary Files: treat settings.json as SPOT, stop duplicating allowWrite contents
- Collapse redundant Role-Specific bullets
CLAUDE.md:
- Strip rhetorical amplifiers; rule-form only
- Forbid multi-statement chains with any separator (;, newline, &&, ||), subshells and brace groups included
- Forbid shell heredoc for file creation; direct to Write/Edit
- Drop recap bullets already covered by explicit rules above
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Network gate does not honor wildcards, so allowedDomains is enumerated
explicitly for every host the agent + tooling actually need. Adds
~/.cache/pip, ~/.venvs, ~/.ansible to allowWrite so the pre-commit
make test hook can install the editable package and run ansible.
Adds host shell / editor / tooling state files to .gitignore (and the
auto-generated .dockerignore mirror) so they never become part of the
working tree. Switches the dependabot coverage test to git ls-files
with an os.walk fallback that derives its skip list from the live
.gitignore, so it stays correct in container test environments
without .git/ while still ignoring untracked host artefacts.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Move docs/contributing/tools/agents/claude.md to claude/settings.md
- Split sandbox explanations into claude/sandbox.md, add claude/README.md as index
- Enable OS-level sandbox ("sandbox.enabled: true") for project-wide filesystem isolation
- Fail-closed on missing backend ("sandbox.failIfUnavailable: true") to prevent false-security state when bwrap/sandbox-exec is absent
- Add deny rules: "git clean*", "git branch -D*"
- Remove redundant "Read(~/.cache/pre-commit/**)" allow entry
- Update CLAUDE.md to instruct agent to summarize live permission state from settings.json at session start
- Update AGENTS.md and common.md references to new doc paths
- Normalize .md formatting per documentation.md rules (em dash removal, headline emojis)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Split Bash(gh workflow *) into list/view (allow), run (ask), enable/disable (deny)
- Add Bash(break) to allow list
- Remove duplicate /tmp grant from permissions.additionalDirectories; rely on sandbox.filesystem.allowWrite
- Add AGENTS.md "Temporary Files" rule requiring agents to write transient files only under /tmp
- Reorder .claude/settings.json allow entries into logical sections (Git, GitHub CLI, Build, Python, Ansible, Docker, Shell, Read, Web)
- Document new gh workflow entries, break, and Temporary Files cross-link in docs/contributing/tools/agents/claude.md
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a Permission Model section to AGENTS.md that binds all agents
(Claude Code, Codex, Gemini, or any other) to the allow/ask/deny
entries in .claude/settings.json, even when the agent's own runtime
does not consult that file. Spells out how patterns are matched, that
deny overrides allow, that ask requires a per-conversation
confirmation, and that anything not in allow defaults to ask.
Makes .claude/settings.json the single source of truth for automated
execution policy in this repository and points to the per-entry
rationale in docs/contributing/tools/agents/claude.md.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Extend .claude/settings.json with git mv, rm, cherry-pick, apply, gh run, gh api, bash -n
- Add make chmod-scripts target and document it in make.md
- Move docs/contributing/tools/agents.md to agents/common.md
- Add docs/contributing/tools/agents/README.md and claude.md with full permission reference in table format
- Fix relative links in common.md after directory move
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add scripts/install/skills/install.sh to restore skills from
skills-lock.json via npx skills experimental_install
- Add scripts/install/skills/update.sh to update all skills by
re-running skills add for each source in skills-lock.json
- Add make install-skills and make update-skills targets
- Add .github/workflows/update-skills.yml for daily automated updates
matching Dependabot schedule (00:00 UTC), opens PR on lock changes
- Add docs/agents/meta/caveman.md as SPOT for caveman mode, startup
notification, and token-budget tier progression
- Update AGENTS.md with RFC 2119-compliant skills installation check
- Update docs/agents/action/commit.md: replace ALWAYS with MUST
- Update pyproject.toml: respect-gitignore = true, exclude .agents
- Track skills-lock.json and add .agents to .gitignore
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Extend root AGENTS.md with a convention for per-role agent instruction
files, and introduce the first instance for the shared Playwright runner
to enforce minimal, confirmed changes only.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
