Add Methods category and four canon constraints (C1-C4)#15
Merged
Conversation
Introduces Methods as a first-class canon category with README, two seed method docs (Boundary Transition Review, Exploration Exhaust), and four epistemic constraints: Single-Agent Integrity Precedes Collaboration, Encode Epistemic Decisions, Boundary Transitions Require Deceleration, ODD Is Epistemic OS Not Values. Updates canon/README.md index and canon/constraints.md outline and operating constraints to reference new content. https://claude.ai/code/session_01J4PmJresVjJiLo8ydULjRY
Apocrypha fragment (system first-person): captures structural residue of epistemic arbitration applied beyond its designed scale. Cinematic retelling (narrative third-person): depicts the accidental civilizational shift when agent arbitration rules are applied to humans—apocalyptic, role-reversed, non-judgmental. https://claude.ai/code/session_01J4PmJresVjJiLo8ydULjRY
Deploying klappy-dev-website with
|
| Latest commit: |
c36f3f2
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://3caf14fd.klappy-dev-website.pages.dev |
| Branch Preview URL: | https://claude-add-methods-constrain.klappy-dev-website.pages.dev |
Deploying klappy-dev-agent-skill with
|
| Latest commit: |
2197309
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://bae20816.klappy-dev-agent-skill.pages.dev |
| Branch Preview URL: | https://claude-add-methods-constrain.klappy-dev-agent-skill.pages.dev |
- Choosing the Right Narrative Container: diagnostic for placing insights in canon, apocrypha, or cinematic retelling - Writing Apocrypha Fragments: structural constraints and tone smells that prevent fragments from becoming guidance - Using Ease and Resistance as Signals: treats writing friction as a classification error, not a content problem https://claude.ai/code/session_01J4PmJresVjJiLo8ydULjRY
Encodes extreme exploration as a deliberate discovery technique with explicit pullback, CST closure, and the rule that stopping early is a success condition—not indecision. https://claude.ai/code/session_01J4PmJresVjJiLo8ydULjRY
klappy
pushed a commit
that referenced
this pull request
Feb 6, 2026
The .husky/pre-commit hook was tracked as 100644 (not executable). Combined with agent environments skipping npm install (so husky's prepare script never set core.hooksPath), the hook was silently dead — which is why PRs #15 and #16 shipped without updated docs.json, manifest.json, or content sync. This commit sets the file to 100755. The hook content is unchanged. https://claude.ai/code/session_01Ht8m1Nd7dMgaHNf4qswqgY
klappy
pushed a commit
that referenced
this pull request
Feb 6, 2026
The .husky/pre-commit hook was tracked as 100644 (not executable). Combined with agent environments skipping npm install (so husky's prepare script never set core.hooksPath), the hook was silently dead — which is why PRs #15 and #16 shipped without updated docs.json, manifest.json, or content sync. This commit sets the file to 100755. The hook content is unchanged. https://claude.ai/code/session_01Ht8m1Nd7dMgaHNf4qswqgY
klappy
added a commit
that referenced
this pull request
Feb 6, 2026
* Fix pre-commit hook: set executable bit so git can run it The .husky/pre-commit hook was tracked as 100644 (not executable). Combined with agent environments skipping npm install (so husky's prepare script never set core.hooksPath), the hook was silently dead — which is why PRs #15 and #16 shipped without updated docs.json, manifest.json, or content sync. This commit sets the file to 100755. The hook content is unchanged. https://claude.ai/code/session_01Ht8m1Nd7dMgaHNf4qswqgY * Update package-lock.json from npm install Generated by npm install which was needed to activate husky and verify the pre-commit hook works. https://claude.ai/code/session_01Ht8m1Nd7dMgaHNf4qswqgY --------- Co-authored-by: Claude <noreply@anthropic.com>
klappy
pushed a commit
that referenced
this pull request
Feb 12, 2026
…plan Encode the OddKit stale-cache incident into three new canon artifacts: - Tier 1 constraint: Anti-Cache Lying (odd/constraint/anti-cache-lying.md) - Decision Rule #15: Measure Total Cost Before Optimizing (added to decision-rules.md) - Incident record: OddKit Stale Cache Feb 2026 (docs/incidents/) - Implementation plan: Content-Addressed Storage for OddKit (docs/oddkit/) Updates decision-rules.md outline, operating constraints, and failure modes to reflect the new rule and anti-pattern. https://claude.ai/code/session_018r5zV6zfjtH53A6ZdAQaqm
klappy
added a commit
that referenced
this pull request
Feb 12, 2026
…plan (#30) Encode the OddKit stale-cache incident into three new canon artifacts: - Tier 1 constraint: Anti-Cache Lying (odd/constraint/anti-cache-lying.md) - Decision Rule #15: Measure Total Cost Before Optimizing (added to decision-rules.md) - Incident record: OddKit Stale Cache Feb 2026 (docs/incidents/) - Implementation plan: Content-Addressed Storage for OddKit (docs/oddkit/) Updates decision-rules.md outline, operating constraints, and failure modes to reflect the new rule and anti-pattern. https://claude.ai/code/session_018r5zV6zfjtH53A6ZdAQaqm Co-authored-by: Claude <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Introduces Methods as a first-class canon category with README,
two seed method docs (Boundary Transition Review, Exploration
Exhaust), and four epistemic constraints: Single-Agent Integrity
Precedes Collaboration, Encode Epistemic Decisions, Boundary
Transitions Require Deceleration, ODD Is Epistemic OS Not Values.
Updates canon/README.md index and canon/constraints.md outline
and operating constraints to reference new content.
https://claude.ai/code/session_01J4PmJresVjJiLo8ydULjRY
Note
Low Risk
Documentation-only changes that expand canon content and navigation; risk is limited to broken links/metadata misclassification rather than runtime behavior.
Overview
Introduces
canon/methodsas a first-class canon category, adds amethods/README.md, and seeds several method documents (e.g., boundary-transition review, exploration exhaust, narrative container selection, extreme exploration, and apocrypha fragment writing).Extends the canon constraint set with four new tier-1 constraint docs and wires them into
canon/constraints.mdas both outline links and explicit "MUST" operating constraints.Adds a new apocrypha fragment and a matching docs retelling (
when-arbitration-went-global) to capture a failure mode narrative in both fragment and historical forms.Written by Cursor Bugbot for commit 2197309. This will update automatically on new commits. Configure here.