- name
SKILL.md
O arquivo da skill permanece no repositório do publicador.
Cole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add athola/claude-night-market --skill night-market-architecture-contract -a cursor -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add athola/claude-night-market --skill night-market-architecture-contract -a claude-code -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add athola/claude-night-market --skill night-market-architecture-contract -a codex -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add athola/claude-night-market --skill night-market-architecture-contract -a grok -yEnvie a mensagem copiada em um chat do Grok Bot. O Bot busca este SKILL.md no GitHub e o adiciona às skills que todos os seus Bots compartilham.
Install this skill: https://github.com/athola/claude-night-market/tree/HEAD/.claude/skills/night-market-architecture-contractDo publicador
This skill records the design decisions that hold claude-night-market
together, the invariants that enforcement code keeps true, and the weak
points that are known and accepted. Read it before proposing a change
that crosses a plugin boundary, touches a hook, adds a skill, or bumps
a version. Every claim cites in-repo evidence: an ADR (Architecture
Decision Record, in docs/adr/), a commit hash, or a checked-in
enforcement file. Verify a citation before relying on it:
git log --oneline -1 <hash>
rg -n "Status" docs/adr/<file>.md
Each of the 23 plugins under plugins/ must install and run alone.
There is no shared registry and no root-level shared library that
plugins import at runtime (ADR-0001, Accepted). Plugins detect each
other at runtime via filesystem checks and must degrade gracefully when
a sibling is absent.
Cross-plugin DRY is an anti-pattern here, and an experiment settled
it. Commit 054e2679 consolidated 1164 lines of
duplicated tasks_manager.py from attune, sanctum, and spec-kit into a
shared root script. It broke plugin self-containment and was reverted
in 29961cd2. The durable fix, d89a55c7, made the copies
per-plugin and intentionally different. docs/dependency-audit.md
records the per-plugin copies as the approved state. Do not re-propose
the consolidation.
Practical test before you extract shared code: if a user installs only one plugin from the marketplace, does your change still work? If not, duplicate the code into each plugin instead.
Claude Code copies an installed plugin into a cache directory and runs
its hooks under the host system Python, which can be as old as 3.9.
The repo itself is Python 3.12 (root pyproject.toml,
requires-python >= 3.12). Only hook scripts and their transitive
import chains carry the 3.9 constraint. Five contract rules follow,
each purchased with an outage:
CI enforcement: .github/workflows/python39-compat.yml runs two
gates with uneven coverage. Gate 1 (ruff UP007, flags 3.10+ union
syntax) covers 12 plugins' hooks/ dirs. Gate 2 (hook test suites
inside a real Python 3.9 venv) covers only 7 plugins: abstract,
conserve, egregore, imbue, leyline, memory-palace, sanctum. herald
ships a Stop hook yet appears in neither gate.
.claude-plugin/marketplace.json is the version source of truth
(1.9.15 as of 2026-07-02). Each plugin carries three manifests that
must stay in sync with it and with each other:
.claude-plugin/plugin.json (name, version, component arrays).claude-plugin/metadata.json (version plus dependency hints)openpackage.yml (cross-framework manifest)Plus pyproject.toml and any __init__.py carrying __version__.
Never hand-edit versions across files. Use the bumper, which finds and
rewrites all of them:
uv run python plugins/sanctum/scripts/update_versions.py <version>
One trap: metadata.json dependencies (for example imbue declaring
"abstract": ">=2.0.0") is a separate semver namespace for capability
compatibility. It does not track the marketplace version and a 2.0.0
there does not mean marketplace 2.0.0 exists.
Claude Code loads every installed skill's description into context at 2% of the context window, with a 16,000-character fallback (ADR-0004, Accepted, updated 2026-05-21). Descriptions that exceed the budget make skills invisible with no error anywhere. That is why:
docs/skill-description-guide.md), enforced by the
validate-description-budget pre-commit hook backed by
plugins/abstract/scripts/validate_budget.py.DEFAULT_BUDGET in plugins/abstract/scripts/validate_budget.py,
overridable via SLASH_COMMAND_TOOL_CHAR_BUDGET). ADR-0004 and
docs/skill-description-guide.md still cite a stale 60,000 figure;
the script is the enforcer. Flag the ADR for an update through
change control.When adding a skill, spend the 160 characters on trigger phrases, not on restating the name.
Decisions, learnings, and audit syntheses are posted to GitHub
Discussions, which act as agent collective memory across sessions
(ADR-0007, Accepted). There is no gh discussion subcommand: all
Discussions access goes through gh api graphql. Release trust is
established by SLSA attestation (Supply-chain Levels for Software
Artifacts) of trust-report.json on master pushes
(.github/workflows/trust-attestation.yml). The original blockchain
design (ERC-8004) was dropped for cost. ADR-0008 is marked Superseded
2026-03-15 and now points at GitHub Attestations. See
night-market-collective-memory for the Discussions workflow.
docs/skill-integration-guide.md defines the role taxonomy used when
judging whether a skill is an orphan or a hub:
A skill with zero inbound Skill() references is only a problem if it
also has no command path and no hook that loads it. Check the role
before archiving anything.
Each row names the enforcement that keeps the invariant true. If you weaken the enforcement, you own the failure mode in the third column.
The two ratchet scripts share one mechanic: they fail a commit only
when the violation count rises above the committed baseline, and they
ask you to lower the baseline when the count drops. Never raise a
baseline to get a commit through. That is routing around change
control. One documented exception: a brand-new library skill
legitimately starts uncalled, and scripts/check_skill_graph_drift.py
(plus the _comment in scripts/skill_graph_baseline.json) instructs
you to raise max_uncalled_libraries to record the 30-day consumer
grace period that .claude/rules/shared-utility-consumer-rule.md
grants. See night-market-change-control.
Stated plainly so nobody rediscovers them the hard way. These are known and open, by decision or by neglect.
Skill-discovery overflow is silent. If total description overhead exceeds the context budget, skills vanish with no error (ADR-0004). The 160-char cap and validator ceiling are preventive guards. There is no runtime detection of overflow.
The quality-gate federation has one real orchestrator. The gate
skills (karpathy-principles, scope-guard, proof-of-work, justify,
rigorous-reasoning, vow-enforcement) are designed to compose, but
only egregore:quality-gate sequences the full pipeline today
(docs/quality-gates.md, "Who currently orchestrates"). Every
other consumer picks gates ad hoc.
docs/project-brief.md, docs/specification.md, and
docs/implementation-plan.md are overwritten each feature cycle.
The current contents describe only the latest cycle (insight-palace
bridge as of 2026-07-02). Past cycles survive only in git history.
Do not cite these files as a permanent record.
Duplicate module names across plugins force per-plugin mypy.
Running mypy plugins/ from the root collides on duplicate module
names (comment in .github/workflows/typecheck.yml). The same
constraint makes root pytest exclude plugins/*
(norecursedirs in root pyproject.toml, and root conftest.py
documents the ImportPathMismatchError). Always run plugin tests
and typechecks per plugin.
mdbook is unpinned in the deploy workflow.
.github/workflows/deploy-book.yml installs mdbook-version: 'latest', so an upstream mdbook release can break the book deploy
with no repo change. Candidate fix: pin a version. Not done as of
2026-07-02.
The autonomous loop rides an undocumented harness behavior.
Egregore continues across turns because its Stop hook returns
{"decision": "block", "reason": ...} and the harness feeds the
reason back as the next instruction. Upstream documents Stop hooks
as a gate on stopping, not as a continuation primitive, and the
sanctioned alternatives (/loop, CronCreate) are session-scoped.
ralph-wiggum rides the same behavior, bounded by an iteration
count. Egregore's cost is bounded as of 9f31a878 (stall
detection, default 3), and the reliance is not. No test can cover the
harness end of it. Full record:
docs/adr/0022-stop-hook-reinjection-as-continuation.md
(2026-08-23).
The reliance stands. What changed is that its failure is now
observable rather than silent.
plugins/egregore/scripts/continuation_baton.py has the session
record each handoff with the deadline by which the next turn should
have started, so reinjection quietly ceasing strands a baton with
the process still alive. That is a distinct signal, where before an
upstream change and a finished run looked the same from outside.
Stranded means stalled rather than old, so a long healthy run never
reads as one. The watchdog does not consume the baton yet, which is
accepted debt in
(2026-08-25).
All 23 records are in docs/adr/. Statuses for 0001 to 0017 were
read from the files on 2026-07-02, and 0018 to 0022 on 2026-08-23.
054e2679 and 29961cd2, and both
commits resolve via git log --oneline -1 <hash>.ls each path in the second column from the repo root with
zero errors.ls docs/adr/*.md | wc -l (17 as of 2026-07-02).rg -m1 '"version"' .claude-plugin/marketplace.json matches
the version in every plugin's plugin.json you spot-check.Compiled 2026-07-02 against repo v1.9.15 on branch
discussions-fix-1.9.14. Skill/plugin counts drift: 198 SKILL.md files
under plugins/ and 23 marketplace plugins at compile time.
Re-verify volatile facts:
# ADR count and statuses
rg -m1 -n "Status" docs/adr/*.md
# Ecosystem version source of truth
rg -m1 '"version"' .claude-plugin/marketplace.json
# Discovery budget numbers (2%, 16k fallback; the ADR still says 60k)
rg -n "16,000|60,000" docs/adr/0004-skill-description-budget-optimization.md
# Enforced validator ceiling (90,000 as of 2026-07-03)
rg -n "DEFAULT_BUDGET" plugins/abstract/scripts/validate_budget.py
# Who orchestrates the gate federation today
rg -n "orchestrat" docs/quality-gates.md
# mdbook still unpinned?
rg -n "mdbook-version" .github/workflows/deploy-book.yml
# Ratchet baselines still present
ls scripts/skill_graph_baseline.json scripts/skill_exit_criteria_baseline.json
# Plugin and skill counts
python3 -c "import json;print(len(json.load(open('.claude-plugin/marketplace.json'))['plugins']))"
find plugins -name SKILL.md | wc -l
States load-bearing decisions, invariants, and weak points. Use when judging a design change. Do not use for gating; use night-market-change-control.
---name: night-market-architecture-contractdescription: States load-bearing decisions, invariants, and weak points. Use when judging a design change. Do not use for…---# .claude/skills/night-market-architecture-contract/SKILL.mdPerguntas frequentes
Baixe .claude/skills/night-market-architecture-contract/SKILL.md do publicador ou copie o caminho e abra o repositório. O PlugMCP lista a skill e não hospeda o arquivo.
O publicador o mantém em https://github.com/athola/claude-night-market.
Claude, Cursor, Codex e Grok Build conseguem ler um SKILL.md que você adiciona a partir do repositório do publicador. O Grok Bot o instala quando você envia em um chat o link da pasta da skill no GitHub.
| Hooks become silent no-ops (this happened, and the only symptom was a starved learning digest) |
docs/adr/0023-continuation-baton-makes-a-dropped-turn-observable.md| 0014 |
| Pensive Review-Skill Consolidation |
| Accepted (sequencing only) |
| 9 review skills, 5 sharing a verdict scaffold. Consolidation sequenced, not done |
| 0015 | Over-Built Orchestrator Skill Simplification | Accepted (data-collection phase) | Collect 30 days of usage data before simplifying over-built skills |
| 0016 | Wire-or-Archive for Three Orphan Skills | Accepted (decisions recorded) | Orphans judged on demand signal, wiring cost, and reference value |
| 0017 | Decisions on Confidence-Tagging and Theory-Building | Accepted (2026-06-18) | No enforcement mechanisms and voluntary use. Supersedes 0012 and 0013 |
| 0018 | Reuse memory-palace's Graph for the Tome Research Engine | Accepted | Tome builds on the existing graph instead of a second one |
| 0019 | Retire docs/superpowers/ and Record Its Shipped Design Decisions | Accepted | The design folder became ADR text; the folder is gone |
| 0020 | Detect a Thin Field with Positive Controls, Not Overlap Estimation | Accepted | Frontier detection uses positive controls, not overlap math |
| 0021 | PR Descriptions Carry Six Dimensions in Two Registers | Accepted (2026-08-12) | Six dimensions, but only some earn a heading |
| 0022 | The Autonomous Loop Continues by Riding the Stop Hook | Accepted, with a named open problem (2026-08-23) | Stop-hook re-injection is the loop. Cost bounded by stall detection; the reliance stays open |