§1  The Claim

Citation-grounded triage
for Solana DAO delegates.

Red flags, treasury impact, stakeholders, and the questions worth asking. For any Solana DAO governance proposal, in 30 seconds. The skill is hard-ruled to never recommend a vote.

§2  A Sample Triage

Marinade MIP-21. Treasury authority change. 4 red flags, every claim cited.

MIP-21 proposed transferring 3,350 mSOL ($586,932) from the DAO treasury to a Council wallet, redirecting protocol fees to that wallet, and committing to monthly MNDE repayments at "equivalent value."1

The triage flagged: vague_kpi (no quantified target for "supporting protocol growth"), missing_milestone (no timeline for when fees revert to DAO), backdoor_permission (Council gains ongoing revenue authority), and technical_risk (no specified valuation methodology for "equivalent MNDE value").2

Six proposal-specific delegate questions. Four stakeholders identified, each cited. Treasury direction internal_transfer, confidence medium. Output: a markdown summary a delegate can read in 30 seconds before opening Realms.

One delegate from the validation cohort, after running this exact triage: "The ambiguity around 'equivalent MNDE value' would have slipped past me on a quick read." Five delegates ran it, five reported strong-yes value. See §5 Voices →
Run it yourself: paste any Solana DAO proposal into the open-source pipeline, get the same structured output. try one →
§3  Mechanism

Proposal in. Structured triage out.

Two phases. The first reads end-to-end and scans systematically for risk categories. The second emits a JSON object with six required sections, every claim grounded in a verbatim citation. No on-chain step in the user-facing tier.

PROPOSAL TEXT §3.1 TRIAGE SKILL §3.2 STRUCTURED OUTPUT
§3.1
off-chain skill

Triage

Reads the full proposal including every appendix. Identifies stakeholders, locates monetary amounts, scans systematically for KPI measurability, milestone bounding, permission changes, supply effects, and off-chain dependencies. Buried permission changes get equal scrutiny to the main body.

step: Read end-to-end observation: Treasury swap + fee redirect inference: Internal transfer with ongoing authority shift
§3.2
structured output

Output

JSON object with six required sections: TL;DR, treasury impact, red flags (categorized + cited + severity-rated), stakeholders, open questions, honest gaps. Vagueness in the source is itself surfaced as a finding. Output renders as markdown a delegate can read in 30 seconds.

"red_flags": [{4 cited}], "stakeholders": [{4 cited}], "questions": [6 specific], "confidence": "medium"
§4  Calibration

How we prevent hallucination.

Hallucination in governance costs delegates real money. The triage carries three load-bearing constraints, encoded as hard rules in the skill prompt. A failure on any one invalidates the output. Citation rate across N=10 live proposals tested on Marinade, Jupiter, and Jito: 100%.

  1. Grounding. Every claim cites the proposal text verbatim, or the claim is omitted. If the skill cannot point to a quote, the finding does not appear.
  2. No interpolation. Don't fill from general DAO knowledge or external context. The triage analyzes what's in the proposal, not what should be.
  3. Vagueness is a finding. Don't paper over soft KPIs, open-ended scope, or missing milestones. Surface them as vague_kpi, unbounded_spend, missing_milestone.
§4 · AXIOMS

The eight categories the skill scans for, each with a verbatim-citation requirement:

  • vague_kpi: success metrics are non-measurable, no baseline, no thresholdflagged + cited
  • unbounded_spend: budget open-ended, no dollar cap, no review triggerflagged + cited
  • missing_milestone: disbursement not tied to deliverables or checkpointsflagged + cited
  • backdoor_permission: authority change buried, omitted from summary, framed innocuouslyflagged + cited
  • centralization: explicit concentration of stake, voting power, fee flow, executive authorityflagged + cited
  • token_dilution: any modification to supply trajectory, regardless of directionflagged + cited
  • technical_risk: oracle dependency, off-chain execution risk, mechanism uncertaintyflagged + cited
  • team_track_record: proposer history materially relevant, undisclosed, or contestedflagged + cited

Honest disclosure is preferred over confident guessing. When the skill cannot resolve a question, it degrades the confidence field and surfaces the gap as open_question or honest_gap rather than fabricating detail. The hard rules are load-bearing in this direction.

§5  Voices

Five active delegates ran a real triage.

Five active Solana DAO delegates ran a PsycheForge triage of Marinade MIP-21 (the recent treasury authority proposal that passed 99.6 / 0.4) and answered four questions about whether the structured format actually helps decision-making. All five reported strong-yes value. Quotes verbatim, names withheld at delegates' request.

"The strongest part of the triage is surfacing hidden implementation assumptions that are easy to gloss over. The ambiguity around 'equivalent MNDE value' would have slipped past me on a quick read."
Builder-perspective delegate · governance-conscious
"Governance proposals often sound economically reasonable while quietly weakening enforcement guarantees. The analysis did a good job exposing the implicit power transfer."
Trust-architecture delegate
"The hard part isn't reading proposals. It's quickly spotting economic downside and incentive shifts. If the tool reliably surfaces that, it saves real time. I'd use it several times a week."
Tokenomics-focused delegate
"Most delegates skim the majority of proposals. If the tool can consistently surface the actual decision-critical risks, that's valuable. Probably daily during active governance cycles."
Multi-DAO active delegate
"During heavy governance cycles, helping people quickly understand 'why this proposal is controversial' is genuinely useful. Community sensemaking, not raw analysis."
Community-builder delegate
5 / 5 reported strong-yes on Q2 ("did this catch something you wouldn't have"). 5 / 5 priced subscription positively in the $20 to $150 monthly range, conditional on calibration discipline. Aggregate report and full anonymized transcripts in the open repo.
§6  Tiers

Three tiers. Same skill, same calibration. Different breadth.

Pricing is calibrated to delegate workflow intensity, not feature gates. Every tier returns the same triage quality on every proposal it covers. The difference is how many DAOs and how much surrounding context.

Lite
$25/ month
Retail delegate, weekly governance reading, sensemaking-leaning.
  • 1–2 DAOs of your choice
  • Full triage on every proposal in those DAOs
  • Citation-grounded, no hallucination
  • Markdown + JSON output
Most cited
Standard
$50/ month
Active delegate, treasury / authority / fee proposal focus, weekly+.
  • Multi-DAO across active Solana governance
  • Everything in Lite
  • Priority on contested votes during active cycles
  • 14-day pilot for early users
Premium
$100/ month
Whale, treasury manager, yield researcher, daily during cycles.
  • Comprehensive coverage across Solana DAOs
  • Everything in Standard
  • Alpha-grade context: on-chain stakeholder lookups, historical pattern surfacing
  • Direct line to the team
What is not different across tiers: the citation-grounding requirement, the hard rule against vote recommendations, the decision-support framing. The skill is the same; the breadth of coverage and depth of context differ. A 14-day pilot is available for early users in exchange for one written interview at the end.
§7  Status

What works. What doesn't. What's paused.

PsycheForge is a PoC. Customer discovery completed 2026-05-05 with 5 anonymized delegate interviews. Real value confirmed. No paying users yet. The public Lite tier is beta-only, not generally available. We expect to learn things in the beta that update the copy on this page.

Works

  • Triage skill produces grounded, cited analysis on real proposals
  • Citation grounding: 100% across N=10 live proposals tested
  • 5 / 5 strong-yes from anonymized delegate validation cohort
  • Calibration discipline: v0.3 regression caught and rolled back same week
  • v0.4 incorporates three corrections from delegate feedback
  • Open-source: skill prompts, test fixtures, validation reports public

Doesn't (yet)

  • Zero paying users
  • Public Lite tier not GA, beta-only
  • No automatic URL fetching for DAO forums
  • Multilingual stress-test still narrow
  • Some DAO coverage partial (Sanctum)

Paused (honest disclosure)

  • Vote-outcome predictions: at N=7 weighted accuracy was 51% (coin-flip)
  • Coin-flip accuracy on contested votes does more damage than missing predictions
  • Returns as a public-facing claim only when N≥50 calibrated accuracy is demonstrable
  • On-chain reputation infrastructure: built, runs on devnet, paused as a marketing claim
  • Until then: triage only
§8  Engagement

Two minutes to a working triage on a proposal you actually care about.

Send a DM with the URL of a Solana DAO proposal you're currently weighing. We reply within 4 hours with a Lite-tier triage of that proposal, free, no commitment. If it changes how you read the proposal, the 14-day pilot is on us in exchange for one short interview at the end. If it doesn't change anything, no follow-up. We're not interested in selling tools that don't earn delegate trust.

Primary path

DM us a proposal URL

Send a Marinade, Jupiter, Jito, or Sanctum proposal link. Free Lite-tier triage back within 4 hours. No card, no commitment.

# on X DM @Psycheforglab subject "Triage request" body <proposal-url> # or via the GitHub repo $ gh issue create --title "Triage: <DAO>-<ID>"
DM @Psycheforglab on X

Run it yourself, open-source

For builders. The whole pipeline is MIT-licensed: skill prompts, test fixtures, validation reports, the Lite-tier wrapper. Self-host with any OpenAI-compatible LLM backend.

# clone & install (no system changes) $ git clone github.com/psycheforge/psycheforge $ ./eval/setup_hermes_local.sh # run on any proposal $ python eval/lite_pilot.py \ --proposal your_proposal.md
Read the quick start