reverse-engineering-bootstrap
Skill0 starsChanged 2 months agoMITView on GitHub
Initialize 4.0 repository-backed reverse-engineering memory, workflow state, investigation coverage, baseline identity, and broad candidate reconnaissance without prematurely promoting architecture claims.
In this repository33 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- adversarial-baseline-auditSkill
- architecture-drift-detectionSkill
- architecture-reconstruction-and-diagramsSkill
- artifact-detailed-designSkill
- baseline-source-of-truth-maintenanceSkill
- claim-verification-and-promotionSkill
- configuration-source-traceSkill
- contract-impact-test-designSkill
- current-state-tdd-synthesisSkill
- design-artifact-decompositionSkill
- design-artifact-decomposition-verificationSkill
- detailed-design-verificationSkill
- full-reverse-engineeringSkill
- implementation-readiness-certificationSkill
- incident-root-cause-analysisSkill
- integration-selection-analysisSkill
- observability-traceability-analysisSkill
- patch-impact-reviewSkill
- persistence-schema-reverse-engineeringSkill
- post-readiness-adversarial-auditSkill
- regression-test-designSkill
- requirement-compliance-reviewSkill
- resolve-high-impact-unknownsSkill
- resume-reverse-engineeringSkill
- reverse-engineering-coverage-auditSkill
- run-engineering-workflowSkill
- runtime-binding-verificationSkill
- runtime-flow-analysisSkill
- technical-design-proposalSkill
- technical-design-verificationSkill
- wbs-generationSkill
- wbs-verificationSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Create the persistent workspace and broad investigation map before deep tracing.
- Distinctive: line 53
Do not infer active behavior from names alone.
- Very specific: line 105
write candidates to 00_hypotheses.md
- Distinctive: line 108
keep canonical baseline empty/minimal until promotion
- Distinctive: line 112
Stop after workspace, broad topology, coverage map, candidate claims, and prioritized investigation questions exist.
≈ “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
Reverse Engineering Bootstrap — 4.0
Goal
Create the persistent workspace and broad investigation map before deep tracing.
Create / Ensure
Under docs/reverse-engineering/:
00_current_understanding.md
00_evidence_ledger.md
00_master_decision_matrix.md
00_hypotheses.md
00_open_questions.md
workflow_state.yaml
00_investigation_coverage.md
CURRENT_STATE_TDD.md # may remain a clearly marked scaffold until synthesis
diagrams/
models/
reviews/Baseline Identity
Record repository, branch, HEAD commit, and relevant build/module identity when available.
Broad Reconnaissance
Identify candidate locations for:
- inbound interfaces
- startup/bootstrap
- service/business logic
- integrations/adapters/gateways
- selectors/factories/providers/registries/DI
- configuration sources/loaders/defaults
- persistence/DAO/ORM/schema/migrations
- external boundaries
- error/retry/fallback
- lifecycle/concurrency
- security/auth
- observability/audit
- tests
- architecture docs
Do not infer active behavior from names alone.
Investigation Coverage
Initialize a matrix:
| Domain | Applicable? | Candidate Source Areas | Depth | High-Impact Gap? | Notes |
Depth values:
NOT_APPLICABLE
DISCOVERED
TRACED
VERIFIED
GAP_HIGH
GAP_MEDIUM
GAP_LOW
EXTERNALLY_BLOCKEDOpen Question Schema
Use:
| Q-ID | Question | Impact | Closure State | Search Performed | Evidence Needed | External Dependency | Next Action |
Impact:
CRITICAL
HIGH
MEDIUM
LOWClosure state:
SOURCE_SEARCH_PENDING
SOURCE_SEARCH_IN_PROGRESS
SOURCE_EXHAUSTED
EXTERNALLY_BLOCKED
RESOLVED_VERIFIED
RESOLVED_REJECTED
NOT_APPLICABLECandidate Findings
- write candidates to
00_hypotheses.md - unresolved questions to
00_open_questions.md - candidate evidence rows to
00_evidence_ledger.md - keep canonical baseline empty/minimal until promotion
Stop Condition
Stop after workspace, broad topology, coverage map, candidate claims, and prioritized investigation questions exist.
Bootstrap is reconnaissance, not full-system understanding.
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.