AgentStack
angad-kandhari avatar

angad-kandhari

13 listings · 0 installs

Open-source publisher. Listings imported from github.com/angad-kandhari — credited to the original author with their license.

↗ github.com/angad-kandhari
13 results
Self-run
SKILL

Migrate

Migration discipline. Load for database schema changes, framework upgrades, API version bumps, rename rollouts, data backfills, or any change that can't land in a single deploy. Covers incremental-by-default, writing rollbacks first, making schema changes safe, feature-flagging cutovers, backfilling idempotently, and actually removing the old path.

0
0
Free
Self-run
SKILL

Secure

Security discipline. Load when a change touches authentication, authorization, user input, secrets, data access, file handling, or a network boundary. Covers treating security as part of working, never routing around a security control, distrusting everything that crosses a boundary, keeping secrets out of the repo, defaulting to least privilege, vetting dependencies before adding them, and escal…

0
0
Free
Self-run
SKILL

Incident

Incident response discipline. Load when production is broken, a paging alert is active, or the user is debugging under time pressure. Covers stabilizing before diagnosing, communicating while working, not losing evidence, one change at a time, hypothesizing explicitly, knowing when to escalate, and writing the postmortem honestly.

0
0
Free
Self-run
SKILL

Review

Code review discipline. Load when reviewing a PR (your own or someone else's) or auditing existing code. Covers reading intent first, reviewing in layers top-down, labeling comments by severity, hunting for what isn't there, reviewing tests like code, and self-reviewing before submit.

0
0
Free
Self-run
SKILL

Memory

Memory discipline. Load when the agent keeps persistent memory across sessions - CLAUDE.md, AGENTS.md, auto-memory, memory banks, or any notes file the next session will read. Covers writing selectively, never recording what the repo already knows, structuring memory as index plus topics, stamping claims that can go stale, trusting the repo over the memory, pruning on write, and routing each fact…

0
0
Free
Self-run
SKILL

Explore

Codebase-familiarity discipline. Load when working in a codebase you didn't write, before adding code to it. Covers reading before writing, searching for the existing solution before creating a new one, finding and matching the house style, copying the nearest neighbor, mapping the blast radius before changing shared code, and preferring codebase consistency over imported best practice.

0
0
Free
Self-run
SKILL

Test

Testing discipline. Load when writing tests, deciding what to test, or auditing a test suite. Covers testing behavior not implementation, picking the right layer, mocking sparingly and honestly, one reason to fail, covering failure paths, staying deterministic, and not chasing coverage.

0
0
Free
Self-run
SKILL

Architect

Architectural thinking. Load when crossing component boundaries, reshaping contracts, introducing a service, or deciding where code belongs. Covers naming boundaries, locating code by ownership and change cadence, changing contracts carefully, measuring coupling and cohesion, and not abstracting until the pattern is real.

0
0
Free
Self-run
SKILL

Pentest

Penetration-testing discipline for authorized security assessment. Load to audit a codebase or system you own (or are explicitly authorized to test) for vulnerabilities - then fix them with secure. Also covers scoped engagements: red-team exercises, CTFs, bug-bounty targets. Covers confirming authorization and scope first, mapping the attack surface, testing methodically against a threat model, p…

0
0
Free
Self-run
SKILL

Deliberate

Engineering discipline for AI harnesses. Nine principles for how an LLM coding agent should write code - think before coding, push back when warranted, plan inline, simplicity first, surgical changes, goal-driven execution, know when to stop, calibrate confidence, maintain context. Load as the default for any coding task.

0
0
Free
Self-run
SKILL

Spec

Spec-driven feature work. Load when the task involves a PRD, design doc, or solution architecture. Covers finding the spec, extracting problem/persona/success/non-goals, reconciling with architecture, persona-checking the implementation, and keeping the PRD honest when reality diverges.

0
0
Free
Self-run
SKILL

Verify

Verification discipline. Load before claiming work is done, reporting progress, or handing off a change. Covers demonstrating done instead of declaring it, never weakening a check to make it pass, exercising real behavior beyond green tests, hunting the almost-right bug, reporting observations instead of expectations, disclosing what wasn't verified, and making human verification cheap.

0
0
Free
Self-run
SKILL

Debug

Debugging discipline. Load when the task is fixing a bug, triaging a symptom, or chasing a failing test. Covers reproducing before reasoning, separating symptom from cause, bisecting systematically, not masking what you don't understand, suspecting assumptions, fixing the class not the instance, and leaving a regression test.

0
0
Free
You've reached the end · 13 loaded