author-mode
Skill0 starsChanged 25 days agoMITView on GitHub
Instructions for the IWE template author: staging channel (testing →
1 other project uses a version of this.
Adopted by
Most recently taken up by
- TserenTserenov/FMT-exocortex-templatetheir own version, first seen Nov 2, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- TserenTserenov/FMT-exocortex-template★ 63same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository51 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-faultSkill
- apply-capturesSkill
- archgateSkill
- artifactorSkill
- audit-docsSkill
- audit-installationSkill
- bottleneck-pickSkill
- check-secretSkill
- consentSkill
- day-closeSkill
- day-openSkill
- decomposeSkill
- diagnoseSkill
- discovery-sessionSkill
- extendSkill
- fpfSkill
- integration-gateSkill
- iwe-bug-reportSkill
- iwe-platform-redteamSkill
- iwe-restoreSkill
- iwe-rules-reviewSkill
- iwe-updateSkill
- keSkill
- kimi-peer-writerSkill
- local-llmSkill
- month-closeSkill
- org-devSkill
- pack-creatorSkill
- pack-newSkill
- peer-conversationSkill
- personal-guide-renderSkill
- personal-guide-startSkill
- platform-bottleneckSkill
- repo-newSkill
- restore-exocortexSkill
- run-protocolSkill
- setup-wakatimeSkill
- skill-creatorSkill
- strategy-sessionSkill
- skill-idSkill
- thinkSkill
- transcribeSkill
- vdvSkill
- verify-hypothesesSkill
- verifySkill
- week-close-pilotSkill
- week-closeSkill
- wp-newSkill
- w-reflectionSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 39
Remove author-specific constants → replace with {{PLACEHOLDER}}
- Very specific: line 42
Update STAGING.md: status → promoted, "Mode" column → mandatory or extension
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/author-mode — IWE Author Mode
Trigger: staging / promote / author / template / extensions
Applies to: template author only (author_mode: true)
§8. Staging (testing → template)
Rules under testing. When validated, they move to the template (L1).
Staging channel
Rule for adding: new behavior in §9 (author) → SIMULTANEOUSLY add a row to STAGING.md (status: testing).
Promotion (at Week Close):
- Review
STAGING.md— are theretestingentries ready for promotion? Readiness (validated) means more than "the author ran it locally" — the rule must pass verification on at least one non-author profile/user of the template (ADR-IWE-014 R8, carrier-replacement test): any personal path/key/assumption of the author that does not survive that replacement is not ready for promotion — it staystestingor moves torejected. - Remove author-specific constants → replace with
{{PLACEHOLDER}} - Mode (ADR-IWE-014 R9, WP-552 Phase 5): ask — is this mandatory for all template installations, or a toggleable marketplace extension? This axis is orthogonal to R8 and is decided independently of readiness from step 1. Toggleable extension → see "Marketplace extension branch" below; mandatory template rule → go directly to step 4.
- Move to
IWE+ commitfeat: promote S-NN from staging - Update
STAGING.md: status →promoted, "Mode" column →mandatoryorextension
Rejection: anything specific to the author environment → status rejected (stays in §9, not promoted). Do not delete from the table — this is a recorded decision.
Marketplace extension branch: promote-common.sh writes the entry to marketplace-manifest.yaml rather than promotion-status.yaml — fields: type (existing Artifact type: Pack, skill, AR.NNN, Role — no new type is created), owner, install_point, permissions, toggleable, conflict_rule, staging_source (reference to the STAGING.md row for auditability — which rule passed the R8 test and when).
§9. Author layer (L3 — my IWE only)
This section is the personal L3 layer.
update.shdoes not touch it during updates.
Add rules and constants here that apply only to your environment.
L1/L2/L3 Architecture:CONTRIBUTING.md §Three Layers.
Extensions Gate (BLOCKING)
For users: customizing Protocols/Skills → ONLY in extensions/*.md.
Directly editing .claude/skills/ or memory/protocol-*.md is an error.
Architectural rationale: platform files (L1) and user extensions (L3) are separate layers. Mixing layers creates brittleness during updates.
Separation: platform → IWE → update.sh. User → extensions/ + params.yaml.
Author (author_mode: true): direct editing of L1 is PERMITTED.
Delivery to FMT: bash $IWE_SCRIPTS/{script|hook|skill}-promote.sh <file> [--dry-run]
CLAUDE.md: bash $IWE_SCRIPTS/template-sync.sh (sync / --dry-run / --check)
Naming (placeholders)
{{GOVERNANCE_REPO}}— personal governance hub${IWE_WORKSPACE:-$HOME/IWE}/— working directory
Blocking rules (author)
Fill in with rules specific to the author environment.
Distinctions (author)
Stored in
memory/distinctions-warm.mdandextensions/. The file.claude/rules/distinctions.mdbelongs to the platform hot layer;update.shpreserves only the explicitly markedUSER-SPACEblock.
<!-- USER-SPACE --><!-- /USER-SPACE -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

