/** The local-report v9 dashboard shell (reference design), embedded verbatim. */ export declare const V9_TEMPLATE = "\n\n\n\n\naih report \u2014 developer console (v9)\n\n\n\n

Enterprise AI Bootstrapping Harnessv9 draft

self-contained \u00B7 generated by aih report \u00B7 developer console
UTC\u00B7\u00B7:\u00B7\u00B7:\u00B7\u00B7Local\u00B7\u00B7:\u00B7\u00B7:\u00B7\u00B7
\n\n
v9Showcases what aih unblocked \u2014 the host/enterprise blockers (TLS, npm, PATH, MCP) it cleared over the period, paired with what's next. Talks the actuals; not-yet-wired panels marked PREVIEW.
\n
\n
\n Harness wiring \u00B7 developer console\n

Wired and healthy,
one gap \u2014 guardrails.

\n

Everything loads, CLIs are in sync, per-turn context has room. The single thing dragging the score is guardrails wiring (40/100) \u2014 there are 5 actions below, ranked.

\n
82/100Solid \u00B7 wiring
\n
\u25B2 +4 vs last runper-turn \u22123%drift 1\u219215 open actions
\n
1,204actions this week\u25B2 +18% wow
\n
usage = recorded AI activity (commits + tool / skill / MCP calls) \u2014 not cost or tokens
\n
Weakest axis: Guardrails 40 \u2014 closing it moves the score most.
\n

Score = harness wiring present + in sync, not rule quality.

\n
\n
\u25C688/100 \u00B7 solid

READY, WITH GAPS \u2014 an agent can start here

The single \"can I start?\" gate: the maturity score above rates harness wiring; this rates whether an agent can make a correct first change on THIS machine right now. A blocker is a hard stop \u2014 the full remediation list is in What to fix first below.

Can I start?

88/100 \u00B7 solid
READY, WITH GAPSan agent can work, but with gaps in the gears
Readiness score88/100 (solid)
Blockersnone
Same gate as aih ready \u2014 machine \u00B7 repo-contract \u00B7 harness-wiring, over aih's read-only probes.

Blockers \u00B7 must fix before an agent can work

clear
No blockersnothing stops an agent from working here
\u26051 high \u00B7 2 med \u00B7 2 low

What to fix first \u2014 5 ranked actions

The spine of this report: every finding below, triaged by leverage, each with the exact command. When this list is empty, the harness is clean \u2014 nothing else here needs your attention.

Wire guardrails

high

Guardrails at 40/100 \u2014 gitleaks config present but the pre-commit hook is not installed (present \u2260 enforced). Highest leverage + closes a real security gap.

aih bootstrap-ai --scope guardrails --apply

Add AGENTS.md

med

Missing bootloader \u2014 codex, opencode, zed cannot load canon here. Only failing adoption check.

aih scaffold --cli codex --apply

Realign drifted canon

med

RULE_ROUTER.md is +42 tok out of sync (2h). Realign before it reaches the other CLIs.

aih bootstrap-ai --apply

Vet context7 MCP egress

low

context7 is a third-party MCP server (sends queries off-box). Confirm it is approved for this repo.

aih mcp --verify

Wire usage + track hooks

low

Activity, trends and time-to-green need the recorder + per-commit snapshots wired.

aih usage --apply && aih track --apply
\u2713quick wins \u00B7 since Jun 1

aih cleared 4 blockers to get you running

This is why aih exists. The runtime your AI tools assume \u2014 corporate TLS trust, npm, PATH, MCP launch \u2014 was broken on this host; aih diagnosed and repaired it, and has kept it green across 12 runs. The cumulative payoff over the period, not just today.

\n

Remediation ledger \u00B7 what aih fixed

runtime green
Runtime is green \u2014 4 blockers clearedthe environment certs / npm / PATH / MCP assume now works
Certificate trust chaincorporate CA \u2192 trusted (registry)fixed \u00B7 3d
npm runtimeself-signed cert in chain \u2192 healedfixed \u00B7 3d
PATH resolutionrg / fd / jq now resolvefixed \u00B7 3d
MCP pre-flightnpx can launch MCP serversfixed \u00B7 2h
Re-run anytime \u2014 aih heal --scope all diagnoses and repairs.
\n

Over the period

run ledger
4blockers cleared
12aih runs
Open blockers over time
5 \u2192 0 since first run \u00B7 Jun 1
\n
01context

Per-turn context is lean \u2014 62% headroom

The cost that matters is what a CLI loads per turn: 12,200 of 32,000 tokens (claude, the heaviest), down 3% since last run. The full on-disk corpus is larger (18,400 tok / 42 files) but never loaded at once.

\n

Per-turn budget

62% free
38%used
Worst CLIclaude \u00B7 12,200
Budget32,000
vs last run\u22123%
19,800 tokens of headroom
\n

Top files in the corpus

6 of 42
  • ai-coding/RULE_ROUTER.md2,140
  • CLAUDE.md1,810
  • rules/agent-behavior-core.md1,560
  • rules/shared-canonical-block.md1,180
  • .cursor/rules/00-canon.mdc980
  • .kiro/steering/00-canon.md640
\n
02actuals

Velocity is up \u2014 23 commits this week

Real git activity: 23 commits in 7d (up from 14), 87 in 30d, net +2,630 LOC, on a 23-day active streak. Per-CLI usage share is the colorful bar below \u2014 actions, not cost.

\n

Commit activity \u00B7 90 days

git history
less
more
237 days
8730 days
23day streak
longest \u00B7 31 days
\n

LOC \u00B7 30d + repo

net +2,630
added
+4,520
removed
\u22121,890
Repo status
  • mainmain2h
  • feat/x+14\u221225m
uncommitted changes
\n

Usage by CLI \u00B7 this week

1,204 actions
claude 62%
codex 16%
cursor 12%
claude 747codex 193cursor 144kiro 72gemini 48
Share of recorded AI activity by CLI (commits + tool/skill/MCP calls). Needs per-tool hooks for non-commit attribution.
\n
03guardrails + ECC

Guardrails present \u2014 but the hook is not enforced

ECC brings the guardrails, agents, skills and hooks; config is not enforcement, though: gitleaks hook is not installed, so the secret scan never runs. Test/source file ratio 61% (file count, not line coverage).

\n

Test coverage

61%
61%file ratio
test64
source105
not line coverage
\n

Guardrail enforcement

1 not enforced
gitleaks config
present
gitleaks hook
MISSING
pre-commit hook
installed
command-policy
active
\n

ECC harness \u00B7 what came along

profile: balanced
11agents
42skills
9rules
4hooks
Stack packs
typescriptweb
guardrails: gitleaks \u00B7 pre-commit \u00B7 command-policy
\n
04integrity

RULE_ROUTER.md drifted \u2014 realign canon

Drift is a real tamper / config-rot signal: one of 5 tracked managed files changed since the last regen and is +42 tokens out of sync. Time-to-green matters here \u2014 the longer it drifts, the more the CLIs diverge.

\n

Drift detection

1 file
1 of 5 tracked files driftedmanaged block changed out of band
2h ago
ai-coding/RULE_ROUTER.md+42 tokdrifted
CLAUDE.md\u00B7synced
.cursor/rules/00-canon.mdc\u00B7synced
\n

Cross-CLI coherence

design
rules
router
mcp
loads
claude
codex
cursor
kiro
Do all CLIs load the same canon? Not computed yet \u2014 needs a cross-CLI diff. The drift check (left) is the real half today.
\n
05MCP plumbing

MCP wired for 4 CLIs \u2014 1 server phones out

aih writes the MCP config per CLI and pre-flight confirms it launches. Supply-chain truth: context7 is third-party egress (your queries leave the box) \u2014 worth an explicit OK. Runtime call volume is not metered, so it is not shown.

\n

Per-CLI wiring \u00B7 pre-flight green

4/11 wired
bootloader
mcp config
loads
claude
codex
cursor
kiro
\n

Servers + egress

1 third-party
code-review-graphlocal
context7third-party
playwrightlocal
githubvendor API
sequential-thinkinglocal
\n
06setup

Setup is complete except AGENTS.md

Point-in-time gate (stays green once met): 8/9 artifacts, 3 AI CLIs runnable (+1 config-only), 5/7 shell tools. On feat/x with uncommitted changes.

\n

Adoption checks

8/9
\u2713context-dir\u2713CLAUDE.md\u2717AGENTS.md\u2713cursor-rules\u2713mcp\u2713gitleaks\u2713pre-commit\u2713claude-settings\u2713devcontainer
\n

Shell + AI tooling

5/7 tools \u00B7 3 CLIs
Shell tools
rgfdjqghsgcombytree
AI CLIs runnable
claudecodexcursorkiro \u25D0
\n
07enterprise

1 blocker needs IT \u2014 ticket ready

External failures (proxy / TLS / npm / MCP) become a tool-neutral, redacted escalation you paste into IT email / ServiceNow. Self-fixable issues stay with you; only true external blockers escalate.

\n

Findings

routed by who acts
self-fix (you)
5
improvement
2
escalation (IT)
1
\n

Escalation ticket \u00B7 copy to IT

1 external blocker
Subject: MCP pre-flight blocked on managed workstation\n\nSummary: aih's MCP servers cannot launch \u2014 `npx` fails behind the\n  corporate TLS proxy (root CA not trusted by Node).\nImpact:  Claude / Cursor / Kiro cannot reach project MCP servers.\nAsk:     Add the corporate root CA to Node (NODE_EXTRA_CA_CERTS)\n  or allowlist registry.npmjs.org.\nAcceptance: `aih heal --scope mcp` exits 0.
\n
08over the period

How it's trending \u2014 and what to measure next

The point of running this weekly. Left: real signals over time (needs aih track hooked). Right: the outcome deltas that prove sustained productivity \u2014 lead time, rework, and time-to-green \u2014 derivable from git, not yet wired.

\n

Trends \u00B7 last 8 samples

needs aih track

Wiring score

72\u219282

Per-turn ctx %

41\u219238%

Drift incidents

stable

Open actions

8\u21925
\n

Outcome deltas

design
Lead time (commit\u2192merge)
1.8 d
Rework / revert rate
6%
Drift time-to-green (MTTR)
3.2 h
External-check MTTR
1.2 d
These are the honest \"did productivity improve\" measures (DORA-style), derivable from the git seam. Not wired yet.
\n
09skill investment

Heavy lifters vs dormant packs

Where skill investment pays off, and what to trim: 6 skills do the work; 5 ECC language packs (go/php/ruby/swift/kotlin) never fire in this TS repo \u2014 dead weight in always-loaded canon. Counts need usage hooks; dormant detection needs a skill-inventory scan.

\n

Heavy lifters \u00B7 30d

263 calls
  • tdd \u00B7 ecc84 calls
  • code-review \u00B7 ecc61 calls
  • plan \u00B7 canon44 calls
  • security-scan \u00B7 ecc38 calls
  • frontend-design \u00B7 canon22 calls
  • learn \u00B7 user14 calls
\n

Dormant \u2014 trim candidates

5 unused
go-reviewphp-reviewruby-reviewswift-reviewkotlin-review
Trimming the unused language packs cuts ~2.8k tok of always-loaded canon.
\n
10skill trust

Skill governance

External skills acquired via aih workspace add, joined to the committed aih-skills.lock.json. Unapproved = on disk without an approval; stale-pin = approved at a commit the source has since moved past.

\n

Skill governance

not available
No external skills are installed and aih-skills.lock.json is absent \u2014 nothing to govern. Acquire one with aih workspace add <source>.
\n
\n
esc
\n\n\n\n";